tooluniverse-data-wrangling

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and parse open/public third‑party data (e.g., requests to NCBI E-utilities, UniProt/EBI, GWAS Catalog TSV, Zenodo records, GBIF/iNaturalist APIs and other public URLs) and to act on that content (download, parse, filter, merge, and run analyses), meaning untrusted web-hosted content can materially influence tool use and next actions.