figma

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly fetches Figma file contents and user-generated comments (see "Get File" and "Get File Comments" endpoints) which are untrusted third‑party content the agent is expected to read and that could contain instructions able to influence subsequent actions (e.g., exports or posting comments).