find-animation-opportunities
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted codebase files, which provides a surface for indirect prompt injection. However, it implements a defensive posture by instructing the agent to treat all repository content as data rather than instructions, specifically directing it to flag and ignore common injection patterns like "ignore previous instructions."
- [PROMPT_INJECTION]: The skill documentation mentions "ignore previous instructions" solely as a negative example for the agent to detect in external data. This is a defensive instruction rather than a functional attempt to bypass the AI's internal safety protocols.
- [SAFE]: The skill is strictly read-only and does not contain any commands for file modification, network communication, or sensitive data access. It serves as a specialized design audit tool with high restraint.
Audit Metadata