animal-friendship
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists solely of markdown instructions and does not contain any executable scripts or code blocks.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates interaction with unfamiliar external services, which introduces a surface for indirect prompt injection from API responses or documentation.
- Ingestion points: Step 2 in
SKILL.md(profiling system habits). - Boundary markers: Step 1 requires restating no-touch boundaries; Pitfalls section warns against brute-forcing.
- Capability inventory: No internal tools or scripts; uses the agent's existing toolset.
- Sanitization: None explicitly defined for external data handling.
Audit Metadata