tooluniverse-target-research

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly and mandatorily fetches and ingests content from open/public third‑party sources—e.g., OpenTargets, UniProt/ChEMBL, and especially literature APIs like PubMed/EuropePMC (see PATH 0 and PATH 8 in SKILL.md)—and the agent is required to read/interpret that content to grade evidence and drive recommendations, so external content can materially influence next actions.