skills/zerob13/skills/test-doctor/Gen Agent Trust Hub

test-doctor

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to record and execute test commands found in the repository (e.g., package scripts, CI workflows). This is a standard and necessary function for a test auditing tool, and the instructions emphasize running only the minimum necessary commands to verify findings.
  • [DATA_EXPOSURE]: The skill requires reading repository files, including source code, tests, fixtures, and documentation. This is localized file access inherent to the skill's purpose as an auditor and does not involve exfiltration to external domains.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an inherent attack surface as it processes untrusted content from the repository (test files, documentation, git history).
  • Ingestion points: Test files, fixtures, configuration, and documentation (found in SKILL.md).
  • Boundary markers: None specified in the prompt template.
  • Capability inventory: File reading, file editing, and execution of test commands (found in SKILL.md).
  • Sanitization: None specified; the skill relies on the agent's native safety layers when processing repo content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 09:20 AM
Security Audit — agent-trust-hub — test-doctor