Archon Manager

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly crawls and ingests public third-party content (e.g., archon:crawl_website on sites like https://nextjs.org/docs and archon:extract_code_examples from GitHub) and then runs RAG queries (archon:perform_rag_query) that cause the agent to read and interpret that untrusted, external content, creating a risk of indirect prompt injection.