skills/liangmiqwq/skills/test-doctor/Gen Agent Trust Hub

test-doctor

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to locate and execute existing test commands within the repository to verify findings or validate proposed changes.
  • [PROMPT_INJECTION]: The skill processes external data from the repository being audited, including test code and documentation, which presents an indirect prompt injection surface.
  • Ingestion points: Test files, project documentation, git history, and configuration files as specified in the 'Build an evidence base' section of SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from following instructions potentially embedded in the analyzed code.
  • Capability inventory: The agent has capabilities to read files, write files (for test refactoring), and execute shell commands (specifically test commands).
  • Sanitization: There is no mention of sanitizing or escaping the content read from the repository before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 09:22 AM
Security Audit — agent-trust-hub — test-doctor