tooluniverse

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

• Third-party content exposure detected (high risk: 0.90). The skill directly fetches and ingests public third‑party content (e.g., GEO_download_dataset, PubMed_search, PubChem/UniProt/PDB/ChEMBL queries) and then has the agent read, summarize, or analyze those results as part of its workflows, which exposes it to untrusted user‑submitted/public web content that could enable indirect prompt injection.