review-animations
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a specialized persona and a rigorous set of animation standards for code review purposes. It does not request or utilize any tools, network access, or file system permissions.\n- [SAFE]: All external references are to well-known and legitimate design resources (animations.dev, easing.dev, easings.co).\n- [SAFE]: No evidence of obfuscation, credential harvesting, or unauthorized command execution was found in the provided files.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted animation code provided by users, which represents an indirect prompt injection surface. However, the risk is negligible due to the lack of exploitable capabilities. \n
- Ingestion points: User-provided code snippets for review (SKILL.md).\n
- Boundary markers: The skill instructs the agent to focus strictly on animation review and decline unrelated tasks.\n
- Capability inventory: No tools, network access, or file write capabilities are defined or allowed.\n
- Sanitization: None, however, the lack of external capabilities prevents exploitation.
Audit Metadata