compliance-checker
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown instructions and reference tables. No scripts, binaries, or executable components are included.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided marketing copy for compliance auditing. While this represents an ingestion point for untrusted data, the skill possesses no tools or capabilities (such as network access, file writing, or subprocess execution) that could be leveraged by a malicious instruction. Evidence: 1. Ingestion points: User-provided copy in audit prompts. 2. Boundary markers: Absent. 3. Capability inventory: None. 4. Sanitization: Absent.
- [SAFE]: Metadata includes a link to the author's GitHub repository for updates. This is a standard practice for attribution and does not involve automated downloads or runtime execution.
Audit Metadata