tooluniverse-immune-repertoire-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 7 epitope-prediction workflow in SKILL.md explicitly queries public databases (calls ToolUniverse IEDB_search_tcells / PubMed_search and directs the user to VDJdb at https://vdjdb.cdr3.net), so the agent ingests and acts on untrusted, user-generated/public web content that can influence downstream decisions.