anima

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection.
  • Ingestion points: External untrusted data enters the agent context through the url parameter in playground-create (type l2c), Figma file identifiers (fileKey, nodesId), and Anima Playground URLs.
  • Boundary markers: The instructions do not define boundary markers or safety directives to ignore potentially malicious instructions embedded in the external content being processed.
  • Capability inventory: The skill includes tools to create playgrounds and publish live web applications or npm packages using the playground-publish tool.
  • Sanitization: There is no mention of sanitizing or filtering instructions from the retrieved external content before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 03:34 PM