review-animations
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review untrusted code provided by users. This creates an attack surface where malicious instructions could be embedded within code comments or string literals to attempt to influence the agent's behavior.
- Ingestion points: User-provided animation code snippets, CSS styles, and motion library code (e.g., Framer Motion) submitted for review in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" guards for the input data being reviewed.
- Capability inventory: Risk is significantly mitigated as the skill includes the
disable-model-invocation: trueflag in its frontmatter, preventing it from calling external tools or other models. There are no scripts, file system operations, or network capabilities. - Sanitization: No input sanitization or filtering logic is specified for the code being reviewed.
Audit Metadata