Back to skill

Security audit

Visibility: plan

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: the completed scan reported no AIG findings, while Skillspector raised several medium-severity cautions; its review was partial because some referenced paths were missing.

The verdict is benign, not risk-free. Before installing, consider the undeclared tool scope, the unpinned install reference, the English-only documentation instruction, and the auto-deploy reference. Skillspector inspected all three listed components but marked its analysis partial because several paths referenced by the skill were missing, so the evidence is incomplete.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx install'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

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 · catalog.json (reported line 852)May include surrounding context.

json
],
      "source": "github.com/davepoon/buildwithclaude CONTRIBUTING.md, scripts/fetch-plugins.js (loaded 2026-11-08)",
      "verified": "yes",
      "notes": "There is no web submit form (/contribute is 404). Merges auto-deploy to buildwithclaude.com."
    },
    {
      "id": "docker-mcp",

The Context7 workflow requires English documentation without user opt-in.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The instruction to “make sure docs are English .md/.mdx” imposes a specific natural language on the user's documentation. The entry neither asks the user to choose English nor clearly documents why an English-only constraint is necessary.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/scan.py (reported line 108)May include surrounding context.

python
def tracked_dirs(root):
    """Folders (relative to root) that hold files git tracks; empty outside a repo."""
    try:
        out = subprocess.run(["git", "-C", root, "ls-files", "-z"], capture_output=True, text=True, timeout=30).stdout
    except (OSError, subprocess.SubprocessError):
        return set()
    return {f[:i] for f in out.split("\0") for i, c in enumerate(f) if c == "/"}

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/scan.py (reported line 227)May include surrounding context.

python
if re.search(r"^(mcp|fastmcp)\b", read(path), re.M):
                hit("mcp-server", rel)
    try:
        origin = subprocess.run(["git", "-C", root, "remote", "get-url", "origin"],
                                capture_output=True, text=True, timeout=5).stdout.strip()
    except (OSError, subprocess.SubprocessError):
        origin = ""

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/scan.py (reported line 233)May include surrounding context.

python
origin = ""
    if "github.com" in origin:
        try:  # a github.com remote may be private; only gh can tell
            private = subprocess.run(["gh", "repo", "view", origin, "--json", "isPrivate", "-q", ".isPrivate"],
                                     capture_output=True, text=True, timeout=10).stdout.strip()
        except (OSError, subprocess.SubprocessError):
            private = ""