devto

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md shows runtime GET requests to the public Dev.to API (e.g., "Get Your Articles" curl to https://dev.to/api/articles/me and "Get Single Article") which retrieve user-generated, untrusted posts that the agent is expected to read/use (IDs, body_markdown) as part of its workflow, so third-party content could influence subsequent actions.