pw-debug-actions

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data (GitHub Action logs and Playwright traces) which may contain malicious instructions designed to influence the agent's code-fixing logic.
  • Ingestion points: Uses gh run view --log-failed to read workflow logs and npx playwright trace to read external trace data (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions are used to separate untrusted CI data from the agent's internal instructions.
  • Capability inventory: The skill can execute shell commands (gh, npx, git) and modify source code files to apply fixes (SKILL.md).
  • Sanitization: The skill does not implement specific sanitization or validation of the downloaded logs or trace content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 11:30 PM
Security Audit — agent-trust-hub — pw-debug-actions