tooluniverse-noncoding-rna

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow and code explicitly instruct the agent to fetch and ingest content from public third‑party sites (e.g., TargetScan via https://www.targetscan.org/... , miRTarBase downloads at mirtarbase.cuhk.edu.cn, PubMed/DisGeNET/GTEx/RNAcentral/LNCipedia queries) and to read/interpret those results to identify/validate targets and drive downstream analyses, which meets the criteria for exposure to untrusted external content that can influence actions.