anima-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from external sources (Figma API and Anima generation output) and writes this content to a local file-based cache. This workflow presents an attack surface where instructions embedded within a Figma design could potentially influence the agent if not properly delimited.
- Ingestion points: The skill fetches design data from
api.figma.comand receives code generated by the Anima service. - Boundary markers: The current implementation does not show explicit boundary markers or instructions to ignore embedded prompts within the fetched design data.
- Capability inventory: The skill has permissions for file system writing (
Write) and shell execution (Bash), which are used to maintain the.anima-cachedirectory. - Sanitization: No explicit sanitization or validation logic is present for the design data retrieved from the Figma API before it is handled by the generation logic.
Audit Metadata