Agent Discovery

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 from third-party sources — e.g., GitHub repos, HuggingFace model pages, LangChain Hub agent templates, arXiv papers and gpt_store entries — as part of agent_discovery/check_compatibility, so untrusted external content can be read and materially influence scanning, compatibility scoring, and integration decisions.