iso-standards-readiness
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied JSON and Markdown files which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Data is ingested from user-provided file paths via scripts such as
scripts/validate_evidence_manifest.pyandscripts/audit_document_records.py. - Boundary markers: The system instructions explicitly mandate that all output be labeled as draft and require human review, although technical delimiters for data interpolation are not utilized.
- Capability inventory: The skill is restricted to reading and writing local text files and performing structural metadata checks. It lacks capabilities for network access, subprocess execution, or dynamic code evaluation.
- Sanitization: The
scripts/_common.pyutility enforces rigorous validation, including limits on file size (2MB), nesting depth (30), and text length (20,000 characters), and it proactively rejects symbolic links and duplicate JSON keys.
Audit Metadata