skills/kcchien/skills/animate/Gen Agent Trust Hub

animate

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to analyze external data (features or components from the codebase or conversation) to provide animation recommendations. This ingestion of untrusted data creates a potential surface for indirect prompt injection where malicious instructions could be embedded in the code or descriptions being reviewed.
  • Ingestion points: Reads component/feature descriptions and code from the thread or codebase as specified in the target argument and the 'Context Gathering' section.
  • Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the ingested content.
  • Capability inventory: The skill primarily generates design strategies and CSS/JS code snippets. It lacks direct capabilities for network access or persistent file system modifications, though it utilizes the AskUserQuestionTool for clarification.
  • Sanitization: There are no explicit sanitization or filtering steps defined for the input data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 03:09 PM