anima-common-errors

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md Diagnostic Script clearly instructs querying the Figma API (curl to https://api.figma.com/v1/me and https://api.figma.com/v1/files/${FIGMA_FILE_KEY}) and parsing fields like .handle and .name, which are untrusted, user-generated third-party content that the agent is expected to read and use to decide next diagnostic actions, creating a risk of indirect prompt injection.