anima-cost-tuning
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a vulnerability surface by instructing the agent to process external data from the Figma API to determine generation policies.
- Ingestion points: External Figma file versions and metadata referenced in the
shouldGeneratelogic (SKILL.md). - Boundary markers: None present in the provided code snippets to delimit external metadata from agent instructions.
- Capability inventory: The skill is granted
Read,Write,Edit, andBash(npm:*)capabilities. - Sanitization: No explicit sanitization or validation of the Figma API response is demonstrated in the implementation logic.
Audit Metadata