skill-integration-tester
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The utility parses workflow definitions from CLAUDE.md, which serves as an external ingestion point for data that could potentially contain malicious instructions.
- Ingestion points: The scripts/validate_workflows.py script reads and parses CLAUDE.md using regular expressions to extract workflow names and steps.
- Boundary markers: The script does not implement delimiters or safety instructions to prevent an agent from following instructions embedded within the source file.
- Capability inventory: The skill is restricted to local file system read operations for metadata validation and write operations for report generation; it lacks network access and command execution capabilities.
- Sanitization: The script extracts text via regex but does not perform sanitization on the content before outputting it into JSON or Markdown reports.
Audit Metadata