tooluniverse-proteomics-analysis

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly queries the public STRING database for interaction data (see PHASE_DETAILS.md Phase 6: "Query STRING for interaction networks" and CODE_REFERENCE.md function build_protein_network which calls ToolUniverse.string_get_interactions to fetch STRING interactions), and that external data is parsed and used to build networks and drive downstream analysis, so it exposes the agent to untrusted third‑party content that can influence actions.