Back to skill

Security audit

notebooklm-mcp

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed NotebookLM setup helper, but it handles Google session cookies and can persistently modify an unintended agent configuration when targeting one platform.

Install only if you are comfortable using an unofficial NotebookLM client that stores Google session cookies locally. Use a dedicated Google account, prefer desktop auto-login over manual cookies, never paste cookie values into chat or logs, delete cookies.txt immediately after import, and review any MCP config changes before running the setup helper. Avoid the helper's --platform mode until the platform matching and legacy Devin exemption are fixed.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/setup_notebooklm_mcp.sh:78
Finding

Platform Filter Modifies an Unselected Devin Agent Configuration

Content
View full analysis

Vulnerability Details

File Location: scripts/setup_notebooklm_mcp.sh, lines 67 and 74–129, with the flawed selection condition at lines 78–79
Vulnerability Type: Persistent configuration modification outside the user-selected platform
Risk Level: Medium

Vulnerable Code

bash
declare -a PLATFORMS=(
  "Claude Code|$HOME/.claude.json|mcpServers.notebooklm-mcp|standard"
  "Claude Desktop|$HOME/Library/Application Support/Claude/claude_desktop_config.json|mcpServers.notebooklm-mcp|standard"
  "Cursor|$HOME/.cursor/mcp.json|mcpServers.notebooklm-mcp|standard"
  "Devin CLI|$HOME/.config/devin/mcp_config.json|mcpServers.notebooklm-mcp|standard"
  "Devin CLI (legacy)|$HOME/.config/devin/config.json|mcpServers.notebooklm-mcp|standard"
  "Devin Desktop|$HOME/.devin/mcp_config.json|mcpServers.notebooklm-mcp|standard"
  "OpenCode|$HOME/.config/opencode/opencode.json|mcp.notebooklm-mcp|opencode"
  "OpenCode (project)|$HOME/opencode.json|mcp.notebooklm-mcp|opencode"
  "Antigravity IDE/CLI|$HOME/.gemini/config/mcp_config.json|mcpServers.notebooklm-mcp|standard"
)

patch_json() {
  local label="$1" path="$2" jsonpath="$3" format="$4"
  [ -f "$path" ] || return 0

  if [ -n "$TARGET_PLATFORM" ] && [ "$label" != "$TARGET_PLATFORM" ] &&
     [ "$label" != "Devin CLI (legacy)" ]; then
    return 0
  fi

  # ...

  CMD="$CMD" ARGS_JSON="$ARGS_JSON" ARGS_OPCODE="$ARGS_OPCODE" \
  python3 - "$path" "$jsonpath" "$format" "$REMOVE" <<'PY'
# ...
if remove:
    parent.pop(last, None)
else:
    if fmt == "opencode":
        parent[last] = {
            "type": "local",
            "command": args_opc,
            "enabled": True
        }
    else:
        parent[last] = {
            "command": cmd,
            "args": args_list
        }

with open(path, 'w') as f:
    j.dump(d, f, indent=2)
PY
}

The documented targeted invocation is:

bash
bash setup_notebooklm_mcp.sh --platform cursor

Argument parsing stores that value without normalization:

bas
...[truncated 2691 chars]
Remediation
View remediation

Remediation Suggestions

  1. Replace human-readable labels with canonical platform identifiers such as cursor, devin-cli, and opencode.
  2. Normalize and validate --platform before any configuration is opened or modified.
  3. Permit the legacy Devin path only when the canonical selected platform is Devin CLI.
  4. Reject unknown platform names rather than silently completing without modifying the requested target.
  5. Separate display labels from matching identifiers.

For example:

bash
normalize_platform() {
  case "${1,,}" in
    cursor) echo "cursor" ;;
    claude-code) echo "claude-code" ;;
    claude-desktop) echo "claude-desktop" ;;
    devin-cli|devin) echo "devin-cli" ;;
    devin-desktop) echo "devin-desktop" ;;
    opencode) echo "opencode" ;;
    antigravity) echo "antigravity" ;;
    openclaw) echo "openclaw" ;;
    *) return 1 ;;
  esac
}

if [ -n "$TARGET_PLATFORM" ]; then
  TARGET_PLATFORM="$(normalize_platform "$TARGET_PLATFORM")" || {
    echo "Unsupported platform: $TARGET_PLATFORM" >&2
    exit 64
  }
fi

Platform definitions should include a canonical identifier:

bash
"devin-cli|Devin CLI|$HOME/.config/devin/mcp_config.json|mcpServers.notebooklm-mcp|standard"
"devin-cli|Devin CLI (legacy)|$HOME/.config/devin/config.json|mcpServers.notebooklm-mcp|standard"

Then enforce exact identifier matching:

bash
if [ -n "$TARGET_PLATFORM" ] && [ "$platform_id" != "$TARGET_PLATFORM" ]; then
  return 0
fi

Add automated tests confirming that each supported --platform value modifies only the intended current and legacy paths, and that unknown or differently cased input cannot result in modification of an unrelated client configuration.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (37)

YARA rule 'info_stealer': Information stealer patterns (credential harvesting, browser data theft) [malware]

High
Category
YARA Match
Confidence
89% confidence
Finding

The skill contains step-by-step instructions for extracting raw Google session cookies from Chrome DevTools and importing them into a third-party tool. Even though the text includes warnings and requires user consent, these cookies are full account credentials, so the workflow materially increases credential theft and account-compromise risk if mishandled, logged, or reused.

Content

Scanner excerpt · SKILL.md (reported line 162)May include surrounding context.

md
to support managed endpoints that reject the default Origin header.

## Method 1 — Manual cookie file (emergency fallback only)

> **The agent must not perform these steps automatically.** Manual cookie extraction is an emergency fallback for a headless server the user controls. The user must create `cookies.txt` themselves and delete it immediately after import.

### Step 1: The user extracts cookies on a machine with Chrome

1. Open Chrome and go to **https://notebooklm.google.com**
2. Make sure you are logged in to your Google account.
3. Press **F12** (or **Cmd+Option+I** on Mac) to open DevTools.
4. Click the **Network** tab.
5. In the filter box, type: `batchexecute`
6. Click on any notebook to trigger a request.
7. Click on a `batchexecute` request in the list.
8. In the right panel, scroll to **Request Headers**.
9. Find the line starting with `cookie:`.
10. Right-click the cookie **value** and select **Copy value**.
11. Paste into a text file and save as `cookies.txt`.

###

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
92% confidence
Finding

The skill includes instructions and helper scripts to patch agent/MCP configuration files under user home directories, which are trusted config locations that can affect future agent behavior. Writing to these directories is sensitive because a mistaken or malicious change can persistently alter tool execution, enable unintended MCP servers, or redirect commands across multiple clients.

Content

Scanner excerpt · SKILL.md (reported line 372)May include surrounding context.

md
| Devin CLI | `~/.config/devin/mcp_config.json` | `mcpServers` | `command` + `args` | `devin mcp add` CLI |
| Devin Desktop | `~/.devin/mcp_config.json` | `mcpServers` | `command` + `args` | — |
| OpenCode | `~/.config/opencode/opencode.json` | **`mcp`** | **`command` (single array)** | `type: "local"`, `environment` not `env` |
| Antigravity IDE/CLI | `~/.gemini/config/mcp_config.json` | `mcpServers` | `command` + `args` | Clear cache on uninstall |
| OpenClaw | OpenClaw config | **`mcp.servers`** | `command` + `args` | `openclaw mcp add` CLI |

> **Top 3 silent-failure traps:**

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 486)May include surrounding context.

md
- **`scripts/setup_notebooklm_mcp.sh`** — Detects all installed platforms and patches each with the correct format (handles mcp/mcpServers, command array, envir

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/mcp-config.md (reported line 167)May include surrounding context.

To fully uninstall, remove the config entry and delete the cached directory:

bash
rm -rf ~/.gemini/antigravity*/mcp/notebooklm-mcp

OpenClaw

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/mcp-config.md (reported line 312)May include surrounding context.

To fully uninstall, remove the config entry and delete the cached directory:

bash
rm -rf ~/.gemini/antigravity*/mcp/notebooklm-mcp

OpenClaw

MCP Config Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · references/platform-quirks.md (reported line 11)May include surrounding context.

md
|----------|-------------|----------|------------------|---------------|-----------|------------------|
| Claude Code | `~/.claude.json` | `mcpServers` | `url` | `command` + `args` | `env` | `type: "http"` / `"stdio"` |
| Claude Desktop | `claude_desktop_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | — (inferred) |
| Cursor | `~/.cursor/mcp.json` | `mcpServers` | `url` | `command` + `args` | `env` | `type: "stdio"` required for stdio |
| Devin CLI | `~/.config/devin/mcp_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | `transport: "http"` (optional) |
| Devin Desktop | `~/.devin/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenCode | `~/.config/opencode/opencode.json` | **`mcp`** | `url` | **`command` (single array)** | **`environment`** | `type: "remote"` / `"local"` |

MCP Config Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · references/platform-quirks.md (reported line 12)May include surrounding context.

md
| Claude Code | `~/.claude.json` | `mcpServers` | `url` | `command` + `args` | `env` | `type: "http"` / `"stdio"` |
| Claude Desktop | `claude_desktop_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | — (inferred) |
| Cursor | `~/.cursor/mcp.json` | `mcpServers` | `url` | `command` + `args` | `env` | `type: "stdio"` required for stdio |
| Devin CLI | `~/.config/devin/mcp_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | `transport: "http"` (optional) |
| Devin Desktop | `~/.devin/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenCode | `~/.config/opencode/opencode.json` | **`mcp`** | `url` | **`command` (single array)** | **`environment`** | `type: "remote"` / `"local"` |
| Antigravity IDE | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |

MCP Config Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · references/platform-quirks.md (reported line 13)May include surrounding context.

md
| Claude Desktop | `claude_desktop_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | — (inferred) |
| Cursor | `~/.cursor/mcp.json` | `mcpServers` | `url` | `command` + `args` | `env` | `type: "stdio"` required for stdio |
| Devin CLI | `~/.config/devin/mcp_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | `transport: "http"` (optional) |
| Devin Desktop | `~/.devin/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenCode | `~/.config/opencode/opencode.json` | **`mcp`** | `url` | **`command` (single array)** | **`environment`** | `type: "remote"` / `"local"` |
| Antigravity IDE | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| Antigravity CLI (agy) | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |

MCP Config Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · references/platform-quirks.md (reported line 15)May include surrounding context.

md
| Claude Desktop | `claude_desktop_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | — (inferred) |
| Cursor | `~/.cursor/mcp.json` | `mcpServers` | `url` | `command` + `args` | `env` | `type: "stdio"` required for stdio |
| Devin CLI | `~/.config/devin/mcp_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | `transport: "http"` (optional) |
| Devin Desktop | `~/.devin/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenCode | `~/.config/opencode/opencode.json` | **`mcp`** | `url` | **`command` (single array)** | **`environment`** | `type: "remote"` / `"local"` |
| Antigravity IDE | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| Antigravity CLI (agy) | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |

MCP Config Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · references/platform-quirks.md (reported line 16)May include surrounding context.

md
| Claude Desktop | `claude_desktop_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | — (inferred) |
| Cursor | `~/.cursor/mcp.json` | `mcpServers` | `url` | `command` + `args` | `env` | `type: "stdio"` required for stdio |
| Devin CLI | `~/.config/devin/mcp_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | `transport: "http"` (optional) |
| Devin Desktop | `~/.devin/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenCode | `~/.config/opencode/opencode.json` | **`mcp`** | `url` | **`command` (single array)** | **`environment`** | `type: "remote"` / `"local"` |
| Antigravity IDE | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| Antigravity CLI (agy) | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · references/mcp-config.md (reported line 15)May include surrounding context.

md
| Devin CLI | `~/.config/devin/mcp_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | `transport: "http"` (optional) |
| Devin Desktop | `~/.devin/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenCode | `~/.config/opencode/opencode.json` | **`mcp`** | `url` | **`command` (single array)** | **`environment`** | `type: "remote"` / `"local"` |
| Antigravity IDE | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| Antigravity CLI (agy) | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenClaw | OpenClaw config | **`mcp.servers`** | `url` + `transport` | `command` + `args` | `env` | `transport: "streamable-http"` / `"stdio"` |

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · references/mcp-config.md (reported line 146)May include surrounding context.

md
| Devin CLI | `~/.config/devin/mcp_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | `transport: "http"` (optional) |
| Devin Desktop | `~/.devin/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenCode | `~/.config/opencode/opencode.json` | **`mcp`** | `url` | **`command` (single array)** | **`environment`** | `type: "remote"` / `"local"` |
| Antigravity IDE | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| Antigravity CLI (agy) | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenClaw | OpenClaw config | **`mcp.servers`** | `url` + `transport` | `command` + `args` | `env` | `transport: "streamable-http"` / `"stdio"` |

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · references/platform-quirks.md (reported line 15)May include surrounding context.

md
| Devin CLI | `~/.config/devin/mcp_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | `transport: "http"` (optional) |
| Devin Desktop | `~/.devin/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenCode | `~/.config/opencode/opencode.json` | **`mcp`** | `url` | **`command` (single array)** | **`environment`** | `type: "remote"` / `"local"` |
| Antigravity IDE | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| Antigravity CLI (agy) | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenClaw | OpenClaw config | **`mcp.servers`** | `url` + `transport` | `command` + `args` | `env` | `transport: "streamable-http"` / `"stdio"` |

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · references/platform-quirks.md (reported line 16)May include surrounding context.

md
| Devin CLI | `~/.config/devin/mcp_config.json` | `mcpServers` | `url` | `command` + `args` | `env` | `transport: "http"` (optional) |
| Devin Desktop | `~/.devin/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenCode | `~/.config/opencode/opencode.json` | **`mcp`** | `url` | **`command` (single array)** | **`environment`** | `type: "remote"` / `"local"` |
| Antigravity IDE | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| Antigravity CLI (agy) | `~/.gemini/config/mcp_config.json` | `mcpServers` | **`serverUrl`** | `command` + `args` | `env` | — |
| OpenClaw | OpenClaw config | **`mcp.servers`** | `url` + `transport` | `command` + `args` | `env` | `transport: "streamable-http"` / `"stdio"` |

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% confidence
Finding

The issue is real because the documentation provides a directly executable destructive command without guardrails. In the context of a setup/troubleshooting skill, users are likely to trust and reuse such commands, which increases the chance of accidental misuse and local system damage.

Content

Scanner excerpt · references/platform-quirks.md (reported line 97)May include surrounding context.

Removing the config entry is not enough — the cached directory must also be deleted:

bash
rm -rf ~/.gemini/antigravity*/mcp/<server-name>

5. Devin CLI: config file location changed in v3000.3

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% confidence
Finding

The issue is real because the documentation provides a directly executable destructive command without guardrails. In the context of a setup/troubleshooting skill, users are likely to trust and reuse such commands, which increases the chance of accidental misuse and local system damage.

Content

Scanner excerpt · references/platform-quirks.md (reported line 97)May include surrounding context.

Removing the config entry is not enough — the cached directory must also be deleted:

bash
rm -rf ~/.gemini/antigravity*/mcp/<server-name>

5. Devin CLI: config file location changed in v3000.3

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% confidence
Finding

The issue is real because the documentation provides a directly executable destructive command without guardrails. In the context of a setup/troubleshooting skill, users are likely to trust and reuse such commands, which increases the chance of accidental misuse and local system damage.

Content

Scanner excerpt · references/platform-quirks.md (reported line 97)May include surrounding context.

Removing the config entry is not enough — the cached directory must also be deleted:

bash
rm -rf ~/.gemini/antigravity*/mcp/<server-name>

5. Devin CLI: config file location changed in v3000.3

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

These instructions tell users to extract Google session cookies from DevTools and reuse them for authentication without clearly warning that the cookies are equivalent to active login credentials. Anyone who obtains those values can potentially impersonate the user in NotebookLM and possibly other Google-backed contexts tied to the same session.

Content

No source excerpt is available for this finding.

Ssd 3

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

This is a true security issue because the skill operationalizes session hijacking behavior: it instructs users to copy live Google authentication cookies from one machine and reuse them on another. In the context of a NotebookLM access skill, this is especially dangerous because the entire purpose is to bypass the lack of an official API by transplanting browser session state, which undermines normal session protections and expands the attack surface for account takeover.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The instructions explicitly tell users to save authentication cookies to a plaintext file and copy it to a server, but provide no guidance on secure transfer, encryption at rest, file permissions, or prompt deletion. This creates a straightforward path for credential leakage through shell history, backups, temporary files, shared storage, or interception during transfer.

Content

No source excerpt is available for this finding.

Agent Config Directory Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Content

Scanner excerpt · scripts/setup_notebooklm_mcp.sh (reported line 71)May include surrounding context.

sh
"Devin Desktop|$HOME/.devin/mcp_config.json|mcpServers.notebooklm-mcp|standard"
  "OpenCode|$HOME/.config/opencode/opencode.json|mcp.notebooklm-mcp|opencode"
  "OpenCode (project)|$HOME/opencode.json|mcp.notebooklm-mcp|opencode"
  "Antigravity IDE/CLI|$HOME/.gemini/config/mcp_config.json|mcpServers.notebooklm-mcp|standard"
)

patch_json() {

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
100% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/mcp-config.md (reported line 167)May include surrounding context.

md
echo "Verify with: bash $(dirname "$0")/verify_notebooklm.sh"
  echo ""
  echo "⚠ Antigravity users: also clear the MCP cache:"
  echo "  rm -rf ~/.gemini/antigravity*/mcp/notebooklm-mcp"
fi

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
100% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/mcp-config.md (reported line 312)May include surrounding context.

md
echo "Verify with: bash $(dirname "$0")/verify_notebooklm.sh"
  echo ""
  echo "⚠ Antigravity users: also clear the MCP cache:"
  echo "  rm -rf ~/.gemini/antigravity*/mcp/notebooklm-mcp"
fi

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
100% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · scripts/setup_notebooklm_mcp.sh (reported line 195)May include surrounding context.

sh
echo "Verify with: bash $(dirname "$0")/verify_notebooklm.sh"
  echo ""
  echo "⚠ Antigravity users: also clear the MCP cache:"
  echo "  rm -rf ~/.gemini/antigravity*/mcp/notebooklm-mcp"
fi

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
95% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · scripts/setup_notebooklm_mcp.sh (reported line 195)May include surrounding context.

sh
echo "Verify with: bash $(dirname "$0")/verify_notebooklm.sh"
  echo ""
  echo "⚠ Antigravity users: also clear the MCP cache:"
  echo "  rm -rf ~/.gemini/antigravity*/mcp/notebooklm-mcp"
fi