bundle-social-posts

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md) and the API reference (references/06-post.md) explicitly instruct the agent to call Bundle.social endpoints like GET /api/v1/post/ and GET /api/v1/post/{id} and to "interpret the response" (full platform-specific post data), which means the agent will ingest user-generated social-post content from a third-party service that could contain untrusted instructions influencing subsequent actions (retry, edit, delete).