capa-officer
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The tool processes external JSON data that could contain prompt injection attempts.
- Ingestion points: The
scripts/capa_tracker.pyscript reads user-supplied CAPA records from a JSON file specified via the--capascommand-line argument. - Boundary markers: The script does not utilize boundary markers or specific 'ignore' instructions when formatting the ingested data into text reports for the agent to read.
- Capability inventory: The script is restricted to standard Python data processing and stdout printing; it has no capabilities for network access, file system writes, or subprocess execution.
- Sanitization: Input strings (such as CAPA descriptions and root cause statements) are used directly in output formatting without escaping or sanitization.
Audit Metadata