data-journalism
Warn
Audited by Snyk on May 11, 2026
Risk Level: MEDIUM
Full Analysis
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 fetching and ingesting public third‑party data (e.g., gpd.read_file('https://example.com/data.geojson'), guidance to "scrap[e] public information" and use public APIs like the U.S. Census geocoder and Google Maps geocode) so the agent would read untrusted, user-provided web content as part of its workflow, which could materially influence analysis and subsequent tool actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata