beehiiv

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

• Third-party content exposure detected (high risk: 0.80). The skill calls Beehiiv's public API (BASE_URL https://api.beehiiv.com/v2) to list and retrieve posts — e.g., GET /publications/{publicationId}/posts/{postId} implemented in dist/commands/get.js and described in docs/get.md — returning full HTML of user-authored posts that the workflow explicitly instructs the agent to read, so untrusted third‑party content can influence subsequent actions.