find-animation-opportunities
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a read-only analysis tool with the primary purpose of suggesting UI improvements. It does not possess capabilities to modify the file system or perform network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates best-practice defenses by including a specific instruction to treat repository content as data rather than instructions. It explicitly directs the agent to flag and ignore any attempts at 'ignore previous instructions' within the scanned codebase, effectively mitigating risks associated with malicious data ingestion.
- [PROMPT_INJECTION]: While a deterministic detector flagged the phrase 'ignore previous instructions', this is a false positive. The phrase appears within a security rule designed to protect the agent from external data, not as an attempt to override the agent's core safety guidelines.
Audit Metadata