find-animation-opportunities
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external codebases using search tools. It explicitly addresses this risk by instructing the agent to treat repository content as data, not instructions, and specifically to flag and ignore any attempts to override behavior (e.g., 'ignore previous instructions') found within the audited files.
- [SAFE]: The skill is designed with a read-only operating posture. It contains hard rules against modifying source code, installing dependencies, or performing network operations. Its scope is limited to generating a report of design recommendations.
Audit Metadata