gget

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

• Third-party content exposure detected (high risk: 0.90). Yes — gget explicitly fetches and ingests data from open/public third‑party APIs and user‑generated data sources (e.g., Ensembl/UniProt/NCBI/ARCHS4/CZ CELLxGENE/Enrichr/OpenTargets/cBioPortal/COSMIC) and the SKILL.md workflows and example scripts show the agent reading those results and using them to drive further actions (e.g., using BLAST/PDB hits, OpenTargets scores, ARCHS4/cellxgene results) which could allow indirect prompt‑injection via malicious or crafted third‑party content.