agenticflow-built-in-credits

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly uses built-in web_search and web_retrieval nodes and blueprints such as summarize-url, competitor-url-snapshot, and rss-digest-email, which fetch and ingest public web/RSS content that the agent will read and act on, allowing untrusted third-party content to influence behavior.