forem-api

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to fetch and process public Forem/DEV.to content (e.g., GET /articles, GET /comments against https://dev.to/api/...), which are untrusted, user-generated posts and comments that the agent would read and interpret as part of its workflow, enabling indirect prompt injection.