behave-like-anion
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill establishes behavioral guidelines that prioritize safety and data integrity, such as explicitly prohibiting harmful commands (e.g., recursive deletion) and preventing unauthorized data leaks.
- [SAFE]: The coding instructions promote security best practices, specifically requiring explicitly pinned versions for reproducibility and security analysis, and avoiding retry loops or redundant fallback mechanisms unless requested by the user.
- [INDIRECT_PROMPT_INJECTION]: The skill mentions reading external logs to investigate issues, which is a potential entry point for external data, but it does so in the context of diagnostic safety and root-cause analysis.
Audit Metadata