security-compliance-compliance-check
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to perform compliance analysis, which presents a risk of indirect prompt injection. 1. Ingestion points: User-provided business context is ingested via the $ARGUMENTS placeholder in SKILL.md. 2. Boundary markers: Absent. The skill lacks explicit delimiters or instructions to ignore embedded commands within user input. 3. Capability inventory: The skill frontmatter does not define allowed-tools, limiting its direct interaction with the host system. 4. Sanitization: Absent. The instructions do not specify any validation or filtering of external data before processing.
Audit Metadata