find-animation-opportunities
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs analysis on codebase files, which constitutes an ingestion point for untrusted data. This surface is mitigated by 'Hard Rule 4', which explicitly instructs the agent to treat repository content as data rather than instructions and to flag/ignore override attempts like 'ignore previous instructions'. Since the skill is strictly read-only and lacks network or file-write capabilities, the risk is minimal.
- [PROMPT_INJECTION]: Static detectors flagged the presence of instructions related to overriding behavior. Analysis confirms these are defensive rules (Hard Rule 4) intended to protect the agent from malicious content in analyzed files, not attempts to bypass platform safety guidelines.
Audit Metadata