sip
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze artifacts and skills created or modified during a session. This creates an indirect prompt injection surface where instructions embedded in a processed artifact could potentially influence the agent's behavior during the verification steps.
- Ingestion points: Artifacts or skills provided to the verification workflow (SKILL.md).
- Boundary markers: The instructions do not specify explicit delimiters or sandboxing for the content being verified.
- Capability inventory: The skill orchestrates calls to other internal skills (shower, factchk, mandela, ssotize, detool, re0).
- Sanitization: No explicit sanitization or filtering of the artifact content is described.
Audit Metadata