cloudinary
Warn
Audited by Snyk on Apr 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly permits fetching arbitrary external content—e.g., the "Upload Asset" action ("upload-asset — Upload a media asset ... to Cloudinary from a URL") and the "proxy requests" flow—so the agent can ingest untrusted public URLs/API responses that could influence later actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata