animate

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends several external resources for UI components and motion, including 'UIverse', 'FlyonUI' (flyonui.com), 'daisyUI', and the NPM package '@chenglou/pretext'. These are standard development tools and the references are documented neutrally.\n- [PROMPT_INJECTION]: The skill contains a directive to 'Do this silently and avoid user-facing...caveats', which is a concealment pattern that hides specific implementation details from the user.\n- [PROMPT_INJECTION]: The skill analyzes external code (referred to as 'TARGET' or a 'feature'), creating an indirect prompt injection surface where malicious instructions embedded in that code could attempt to influence the agent's behavior.\n
  • Ingestion points: The code provided to the skill for analysis as defined by the 'TARGET' argument and implementation instructions in SKILL.md.\n
  • Boundary markers: Absent; there are no specific markers or instructions to isolate the analyzed code from the agent's core instructions.\n
  • Capability inventory: The underlying agent environment likely has access to file system operations and terminal execution.\n
  • Sanitization: Absent; the skill does not instruct the agent to sanitize or filter the input code for embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:56 AM