klingai-compliance-review
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reviewing user-provided artifacts or "canaries" for policy compliance. Processing these external inputs constitutes an indirect prompt injection surface.
- Ingestion points: Artifacts and review scopes described in the instructions section of
SKILL.md. - Boundary markers: None explicitly defined in the provided code snippets or instructions.
- Capability inventory: Access to
Read,Write,Edit,Bash, andGreptools to facilitate the review process and report generation. - Sanitization: The instructions contain explicit mandates to reject artifacts containing private information, unlicensed material, or restricted content, acting as a procedural safeguard.
Audit Metadata