scout-message-triage
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates entirely locally using deterministic Python scripts. No network activity, external downloads, or suspicious file system operations were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes external scout message data provided in JSON format. The risk is minimized by strict input validation and lack of dangerous capabilities.\n
- Ingestion points:
scripts/triage_scouts.pyprocesses data from an input JSON file.\n - Boundary markers: The script uses structured JSON fields which inherently separate data from instructions.\n
- Capability inventory: The skill is limited to local JSON parsing and console output; it contains no subprocess calls, file-write operations, or network capabilities across its scripts.\n
- Sanitization: The
parse_scoutfunction inscripts/triage_scouts.pyenforces strict type validation and schema checking on all ingested data.
Audit Metadata