code-vuln-audit

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/security_scan.py uses subprocess.run to invoke external security tools as part of its core functionality.
  • It executes npm audit for Node.js projects and pip-audit for Python projects.
  • The execution is performed safely using argument lists, which prevents shell injection.
  • The script uses shutil.which to resolve the full path of the executables from the system environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external code files during its scanning phase, which creates a vulnerability surface for indirect prompt injection.
  • Ingestion points: The walk_files and read_lines functions in scripts/security_scan.py ingest content from all files within the user-provided target directory.
  • Boundary markers: The scanner generates a structured text or JSON report. While it provides context for findings, it lacks explicit delimiters or instructions to the agent to ignore potentially malicious instructions embedded within the scanned code snippets.
  • Capability inventory: The skill can execute local commands via subprocess.run (limited to npm and pip-audit) and read arbitrary files in the target directory.
  • Sanitization: Discovered code snippets containing potential vulnerabilities are truncated to a maximum of 200 characters before being included in the final report.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:12 AM