anima-sdk-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for ingesting design data from the Anima API and writing generated code to the local file system, creating a vulnerability surface where malicious design metadata could influence the agent's behavior. \n
- Ingestion points: Design data is fetched via the
@animaapp/anima-sdkinsrc/anima/retry.tsandsrc/anima/cache.ts. \n - Boundary markers: The instructions recommend using an allowlist for input file/node IDs and a sandbox Figma file. \n
- Capability inventory: The skill utilizes the
fsmodule for directory creation and file writes insrc/anima/cache.ts. \n - Sanitization: The skill advises redacting configuration errors and blocking publication if normalization fails. \n- [SAFE]: The skill implements secure secret management patterns, explicitly instructing to inject credentials via environment variables and preventing them from being logged or cached. \n- [SAFE]: Downloads and references to the
@animaapp/anima-sdkpackage and official Anima documentation are from a well-known service.
Audit Metadata