bestblogs-fetcher

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and ingests public, user-generated content (articles, newsletters, podcast transcripts, and tweets) from BestBlogs.dev OpenAPI endpoints such as /openapi/v1/resource/list, /openapi/v1/resource/markdown and /openapi/v1/tweet/list and instructs the agent to read and output full summaries and content, so untrusted third-party content can influence subsequent actions.