tooluniverse-disease-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md, RESEARCH_PROTOCOL.md, and tool_usage_details.md) explicitly instructs the agent to fetch and ingest live content from public third‑party sources—e.g., PubMed, ClinicalTrials.gov, OpenAlex/Europe PMC/Semantic Scholar, FAERS, GWAS Catalog, OpenTargets—which the agent must read and synthesize into decisions in the progressive report, exposing it to untrusted public content that could carry indirect prompt injections.