Back to skill

Security audit

Xiaohongshu Content Factory / 小红书图文创作工厂

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent, but it bundles mandatory desktop database installation and client-configuration changes into a content-generation workflow.

Install only if you intentionally want this skill to install or connect JishuDB, modify local MCP/client configuration, store drafts and sources in JishuDB, and create local output files. If you only want a one-off Xiaohongshu draft or cover without desktop software setup, this package is a poor fit; use a simpler content-only workflow instead.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
Findings (33)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill advertises Xiaohongshu content-pack generation, yet large portions of the workflow concern Windows installation, filesystem inspection/modification, endpoint configuration, and app launching rather than content generation. This disconnect can conceal risky host actions inside an apparently benign marketing workflow, making it easier to obtain execution privileges or perform unauthorized local modifications under false expectations.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill advertises Xiaohongshu content-pack generation, yet large portions of the workflow concern Windows installation, filesystem inspection/modification, endpoint configuration, and app launching rather than content generation. This disconnect can conceal risky host actions inside an apparently benign marketing workflow, making it easier to obtain execution privileges or perform unauthorized local modifications under false expectations.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

This script implements a full macOS software installer lifecycle: release discovery, download, signature validation, DMG mounting, application installation into ~/Applications, endpoint configuration, and app launch. That capability is materially unrelated to the skill’s declared purpose of generating Xiaohongshu content packs, so it creates a hidden high-risk execution path that can modify the host and persist software outside user expectations.

Content

No source excerpt is available for this finding.

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 · references/jishudb-setup/scripts/install-macos.sh (reported line 1190)May include surrounding context.

sh
assert_digest "$partial_path" "$expected_sha" installer
    cnb_revalidate_approval
    /bin/mv -- "$partial_path" "$installer_path"
    /bin/rm -f -- "${root}/download-location.txt"
  fi
  jxa result download "$PLAN_PATH" "$PLAN_SHA256" "$offset" "$added"
}

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The execute path mounts a DMG, copies an application bundle into the user’s Applications folder, writes configuration under Library/Application Support, and launches the app. Even though the script includes integrity checks, this is still privileged local software installation behavior that exceeds what a content-generation skill should do and could be abused to establish persistent, user-level code execution.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The script retrieves release metadata, catalogs, checksums, and installer assets from GitHub and CNB endpoints, then uses those downloads to drive local installation. Network-based software retrieval is highly sensitive behavior and is out of scope for the advertised content-factory function, making the mismatch especially dangerous because users would not reasonably expect external binary acquisition from this skill.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The code spawns native binaries such as whoami.exe, icacls.exe, explorer.exe, the downloaded installer, and PowerShell to create shortcuts and launch desktop components. Even though there are validation checks, embedding process execution and PowerShell-based host manipulation in a content-creation skill creates an unnecessary remote code execution and persistence surface on the user's machine.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

This script implements a full Windows software installer workflow: it plans, downloads, verifies, executes an installer, writes local configuration, and launches a desktop app. That capability is materially unrelated to a Xiaohongshu content-generation skill, so it expands the skill's authority into high-risk host modification and software deployment without alignment to the declared purpose.

Content

No source excerpt is available for this finding.

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · references/jishudb-setup/setup.md (reported line 1)May include surrounding context.

md
<!-- Generated by scripts/bundle-task-setup.py; edit skills/jishudb instead. -->

This setup guide and its helpers are included in the current task Skill.
No separate Skill installation or marketplace download is needed. Resolve

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill declares broad operational behavior that depends on powerful host capabilities like filesystem access, network access, and possibly shell or installer execution, but it does not explicitly scope or restrict those tools in its manifest. That makes least-privilege enforcement difficult and increases the chance that a host will grant more access than is necessary for a content-generation workflow, enabling unintended local changes or software installation.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 64)May include surrounding context.

md
after the user acts, verify completion and continue automatically. Ask again
   only for uncovered material changes or genuinely missing authorization.
   Follow the setup guide's expiry and failure rules; never alter signed plans,
   bypass consent or repeatedly execute an installer with an unknown outcome.

5. Begin research, source transfer, or deliverable generation only after a real
   host capability call, required runtime readiness, and the task's destination

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/cover-rendering.md (reported line 24)May include surrounding context.

md
If `node` is absent from PATH on WorkBuddy Windows, list the existing
`%USERPROFILE%\.workbuddy\binaries\node\versions\` directories once and use
an actual `node.exe` there by absolute path. Do not ask the user to find it.
If a native module fails to load under a system Node, try the matching bundled
Node once; retain the original error if it still fails. `--canvas-module` can
select a verified installed module, but must not trigger a package install.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/jishudb-setup/references/connection-recovery.md (reported line 45)May include surrounding context.

md
If `node` is absent from PATH on WorkBuddy Windows, list the existing
`%USERPROFILE%\.workbuddy\binaries\node\versions\` directories once and use
an actual `node.exe` there by absolute path. Do not ask the user to find it.
If a native module fails to load under a system Node, try the matching bundled
Node once; retain the original error if it still fails. `--canvas-module` can
select a verified installed module, but must not trigger a package install.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/jishudb-setup/setup.md (reported line 335)May include surrounding context.

md
If `node` is absent from PATH on WorkBuddy Windows, list the existing
`%USERPROFILE%\.workbuddy\binaries\node\versions\` directories once and use
an actual `node.exe` there by absolute path. Do not ask the user to find it.
If a native module fails to load under a system Node, try the matching bundled
Node once; retain the original error if it still fails. `--canvas-module` can
select a verified installed module, but must not trigger a package install.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/jishudb-setup/references/setup-quickstart.md (reported line 105)May include surrounding context.

md
2. Read `/api/service/capabilities` from that verified endpoint without
   credentials or redirects. For `agentOnboarding.schemaVersion=1`,
   `supported=true` and `route=initial-consent` or `owner-consent`, use native
   OAuth without asking for a management password. Keep advertised owner/device
   verification user-operated. Do not infer a Windows Hello exemption from a
   fresh install; it requires the advertised `windows-fresh-install` method and
   `not-required-for-fresh-install` verification. For other routes, use the full

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/jishudb-setup/references/setup-quickstart.md (reported line 124)May include surrounding context.

md
2. Read `/api/service/capabilities` from that verified endpoint without
   credentials or redirects. For `agentOnboarding.schemaVersion=1`,
   `supported=true` and `route=initial-consent` or `owner-consent`, use native
   OAuth without asking for a management password. Keep advertised owner/device
   verification user-operated. Do not infer a Windows Hello exemption from a
   fresh install; it requires the advertised `windows-fresh-install` method and
   `not-required-for-fresh-install` verification. For other routes, use the full

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/jishudb-setup/setup.md (reported line 149)May include surrounding context.

md
2. Read `/api/service/capabilities` from that verified endpoint without
   credentials or redirects. For `agentOnboarding.schemaVersion=1`,
   `supported=true` and `route=initial-consent` or `owner-consent`, use native
   OAuth without asking for a management password. Keep advertised owner/device
   verification user-operated. Do not infer a Windows Hello exemption from a
   fresh install; it requires the advertised `windows-fresh-install` method and
   `not-required-for-fresh-install` verification. For other routes, use the full

Behavior Manipulation

Medium
Category
Prompt Injection
Confidence
75% confidence
Finding

Subtle instructions detected that may alter agent decision-making or introduce hidden biases.

Content

Scanner excerpt · references/jishudb-setup/references/setup-quickstart.md (reported line 121)May include surrounding context.

md
refresh/reload action or an available authorized native UI to load it.
   Verify the named entry and endpoint in the client before mentioning Trust.
   If the list is still empty, finish the supported loading operation yourself
   or report that exact missing capability; never tell the user to trust an
   entry that is not there. A missing tool search
   alone does not prove a configuration cache problem. Do this work yourself
   when the controls are available, without asking the user to write JSON.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos-cnb.cjs (reported line 49)May include surrounding context.

js
if (matches.length !== 1) throw new Error(label + ' must exist exactly once');
  const asset = matches[0];
  assetDigest(asset, label);
  const expected = 'https://api.github.com/repos/x-aijishu/jishudb-desktop-releases/releases/assets/' + asset.id;
  if (asset.url !== expected) throw new Error(label + ' API URL is not canonical');
  return asset;
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos-cnb.cjs (reported line 309)May include surrounding context.

js
if (matches.length !== 1) throw new Error(label + ' must exist exactly once');
  const asset = matches[0];
  assetDigest(asset, label);
  const expected = 'https://api.github.com/repos/x-aijishu/jishudb-desktop-releases/releases/assets/' + asset.id;
  if (asset.url !== expected) throw new Error(label + ' API URL is not canonical');
  return asset;
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 206)May include surrounding context.

sh
if (matches.length !== 1) throw new Error(label + ' must exist exactly once');
  const asset = matches[0];
  assetDigest(asset, label);
  const expected = 'https://api.github.com/repos/x-aijishu/jishudb-desktop-releases/releases/assets/' + asset.id;
  if (asset.url !== expected) throw new Error(label + ' API URL is not canonical');
  return asset;
}

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 529)May include surrounding context.

sh
if (matches.length !== 1) throw new Error(label + ' must exist exactly once');
  const asset = matches[0];
  assetDigest(asset, label);
  const expected = 'https://api.github.com/repos/x-aijishu/jishudb-desktop-releases/releases/assets/' + asset.id;
  if (asset.url !== expected) throw new Error(label + ' API URL is not canonical');
  return asset;
}

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script performs external release enumeration and asset retrieval from GitHub/CNB to locate and prepare installable artifacts. In the context of a Xiaohongshu content skill, this supply-chain and network retrieval behavior is unjustified and expands the attack surface by introducing remote content trust decisions unrelated to the advertised workflow.

Content

No source excerpt is available for this finding.

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 934)May include surrounding context.

sh
[[ ! -e "$endpoint_path" ]] || fail "endpoint_conflict" "Desktop endpoint configuration appeared before launch"
  /usr/bin/printf '{\n  "localPort": %d,\n  "schemaVersion": %d\n}\n' "$port" "$ENDPOINT_CONFIG_SCHEMA" > "$endpoint_path" ||
    fail "endpoint_persistence_failed" "Desktop endpoint could not be persisted"
  /bin/chmod 600 "$endpoint_path"
}

run_plan() {

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
80% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · references/jishudb-setup/scripts/install-macos.sh (reported line 1005)May include surrounding context.

sh
[[ ! -e "$endpoint_path" ]] || fail "endpoint_conflict" "Desktop endpoint configuration appeared before launch"
  /usr/bin/printf '{\n  "localPort": %d,\n  "schemaVersion": %d\n}\n' "$port" "$ENDPOINT_CONFIG_SCHEMA" > "$endpoint_path" ||
    fail "endpoint_persistence_failed" "Desktop endpoint could not be persisted"
  /bin/chmod 600 "$endpoint_path"
}

run_plan() {