skills/iwanhe/pandawa/skill-tester/Gen Agent Trust Hub

skill-tester

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill acts as a test runner that executes Python scripts located in target directories. It uses subprocess.run with a defined timeout and performs a pre-execution analysis of import statements to ensure only Python standard library modules are utilized, reducing the risk of unauthorized external code execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external files (Markdown and Python source code) to generate validation reports. It follows best practices by using structured evaluation metrics and does not directly interpolate untrusted content into active prompt instructions. As a quality assurance tool, it serves as a controlled ingestion point for external data.
  • [REMOTE_CODE_EXECUTION]: Not detected. The skill is designed for local filesystem operations and explicitly avoids network dependencies, as noted in its documentation and implementation which uses only the Python standard library.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:33 PM
Security Audit — agent-trust-hub — skill-tester