NYC

qa-expert

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill exhibits an indirect prompt injection surface. The utility scripts scripts/generate_test_plan.py and scripts/coverage_analysis.py take user input via command-line arguments and interpolate it directly into Markdown templates without sanitization. If the agent later reads these generated files, it could execute instructions embedded by a malicious user. \n
  • Ingestion points: CLI arguments --name and --owner in both Python scripts. \n
  • Boundary markers: Absent; the generated markdown does not use delimiters to isolate user-provided content. \n
  • Capability inventory: The skill is granted broad permissions including Bash, Write, and WebFetch tools. \n
  • Sanitization: Absent; input strings are directly inserted into the markdown output.\n- [COMMAND_EXECUTION] (SAFE): The skill documentation suggests using standard development commands (e.g., npm audit, npm test, npm run lint) for quality gates. These are standard practices and are not executed automatically in a hidden or malicious manner.\n- [EXTERNAL_DOWNLOADS] (SAFE): Links to external resources like the Google Testing Blog are provided for documentation purposes only. No automated script downloads or remote code execution patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:10 PM