managing-intelligence-lifecycle
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests intelligence requirements, collection sources, and product metadata from local JSON files (pirs.json, sources.json, products.json). Maliciously crafted data in these files could influence the assessment results or report generation. (1) Ingestion points: load_intelligence_requirements, evaluate_collection_sources, and track_intelligence_products functions in scripts/agent.py. (2) Boundary markers: None identified in the processing logic. (3) Capability inventory: Local file system read and write operations via Python's json and os modules. (4) Sanitization: No input validation or sanitization is performed on the ingested JSON data.
- [EXTERNAL_DOWNLOADS]: The documentation references official API endpoints and repositories for established threat intelligence platforms and standards organizations, including MITRE ATT&CK, NIST, Recorded Future, MISP, and OpenCTI. These are standard resources for cyber threat intelligence professionals.
Audit Metadata