review-animations
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and analyzes external code snippets provided by users, which serves as an untrusted data ingestion point.
- Ingestion points: Code diffs and animation-related scripts provided by the user for review (as indicated in SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or safety warnings to separate user-provided code from the agent's core instructions.
- Capability inventory: The skill is limited to generating textual feedback, markdown tables, and structured verdicts based on the provided code.
- Sanitization: There is no explicit sanitization of the input code, but the skill's narrow operational scope and rigid output requirements mitigate the risk of instructions embedded in code comments influencing agent behavior.
Audit Metadata