tooluniverse-proteomics-data-retrieval

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

• Third-party content exposure detected (high risk: 0.90). This skill's required workflow (Phase 1 and Phase 2 in SKILL.md) explicitly calls ProteomeXchange_search_datasets and MassIVE_get_dataset to fetch metadata from public repositories (ProteomeXchange, MassIVE/PRIDE), i.e., untrusted user-contributed web content that the agent ingests and uses to select/prioritize datasets and drive next actions, which could enable indirect prompt injection.