legal-identity-notices
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from site footers, terms, and manifests (SKILL.md). Ingestion points: Footer, about, contact, and license files. Boundary markers: Evidence labels (OBSERVED, DECLARED) are required to track data provenance. Capability inventory: Manifest inspection for licenses and link verification tools. Sanitization: Prohibits data invention and requires citation of official sources (references/official-sources.md).
- [SAFE]: The skill references established regulatory and standards-body domains (e.g., eur-lex.europa.eu, ftc.gov, w3.org) for requirement verification, which is appropriate for its intended auditing purpose.
Audit Metadata