triage-scout
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources and could be vulnerable to malicious instructions embedded in that content.
- Ingestion points: External data retrieved from the assigned surface during search as described in the Procedure section of SKILL.md.
- Boundary markers: Absent; the template does not provide specific delimiters or instructions for the agent to distinguish between its own instructions and content fetched from external sources.
- Capability inventory: The skill utilizes the kanban_create tool and writes files to the local profile vault directory.
- Sanitization: While the skill advises dropping low-signal noise, it lacks formal technical sanitization or escaping of external content before interpolation into reports.
Audit Metadata