columbia-clio
Warn
Audited by Snyk on Jun 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow calls Columbia’s public Blacklight JSON API endpoints (
https://clio.columbia.edu/catalog.json?...and/catalog/{id}.json), ingesting catalog record text authored by third parties (outsider source) into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata