review-animations
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a passive advisor for motion code quality. It does not contain any executable scripts, command-line operations, or persistence mechanisms.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns, such as downloading and executing scripts from external URLs, were identified in the skill files.
- [OBFUSCATION]: The skill files were scanned for hidden URLs, Base64 encoding, zero-width characters, and homoglyphs; no obfuscation techniques were detected. All external references are provided in plain text.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied code, but the risk of indirect injection is mitigated by the lack of high-privilege capabilities.
- Ingestion points: User-provided motion code diffs evaluated against standards in SKILL.md.
- Boundary markers: No specific delimiters are defined to isolate user code from agent instructions.
- Capability inventory: The skill is limited to text generation; it has no access to network tools, file writing, or shell execution (further restricted by disable-model-invocation: true).
- Sanitization: No input sanitization or filtering is implemented in the skill instructions.
Audit Metadata