coverage

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the local workspace to identify coverage gaps.
  • Ingestion points: The agent scans route definitions (Next.js app/), React/Vue components, API route files, and test specifications (*.spec.ts, *.spec.js) in the project directory (SKILL.md, Steps 1 & 2).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing the contents of these files.
  • Capability inventory: The skill uses the Explore subagent for cataloging and can invoke /pw:generate to create new test files based on its analysis (SKILL.md, Step 6).
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the file contents before they are incorporated into the agent's context or used to generate new code.
  • Risk: If the scanned source files or existing tests contain malicious instructions (e.g., hidden in comments), they could potentially influence the generated coverage matrix or the logic of newly generated tests.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 03:47 AM
Security Audit — agent-trust-hub — coverage