The Agent Skills Directory

[SAFE]: The skill follows security best practices for secret management by instructing the user to store API tokens in a .env file, ensuring the file is added to .gitignore, and using chmod 600 to restrict file access to the owner only.
[EXTERNAL_DOWNLOADS]: The skill installs the @animaapp/anima-sdk package from npm and references official documentation and repositories from Anima and Figma. These are well-known technology services, and the references are documented neutrally as they align with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill enables an attack surface for indirect prompt injection as it processes external Figma design data to generate code.
Ingestion points: Figma file metadata and node data are ingested via the anima.generateCode method in src/anima-client.ts.
Boundary markers: None explicitly present in the provided verification script to delimit external content.
Capability inventory: The skill uses Bash for installation and secret configuration, and the SDK performs network operations to fetch design data.
Sanitization: No explicit sanitization of the generated code content is demonstrated in the verification script.
Assessment: The risk is inherent to the primary purpose of a design-to-code utility and is considered a low-severity architectural characteristic rather than a specific malicious finding.

anima-install-auth