801-regulations-eu-ai-act
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a documentation and template-based extension designed for regulatory assessment. It contains no executable scripts, dynamic code generation, or network-active commands that could pose a security risk to the host system.
- [CREDENTIALS_UNSAFE]: The skill incorporates strong security best practices by explicitly instructing the agent to redact secrets, passwords, and API keys from all evidence collections and reports, substituting them with the
[REDACTED_SECRET]placeholder. This mitigates the risk of accidental credential exposure during the review process. - [INDIRECT_PROMPT_INJECTION]: The skill includes defensive instructions for agents to prioritize 'trusted local project evidence' and 'maintainer-approved sanitized facts' over free-form or external input. This structure reduces the surface area for indirect prompt injection attacks when the agent reviews external codebases or documentation.
Audit Metadata