nanograph-ops
Warn
Audited by Snyk on Apr 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly documents that nanograph will fetch http:// and https:// media URIs and "embed" them inline (see "Blobs and media" in SKILL.md and references/blobs.md), meaning the agent ingests arbitrary public URLs' content and uses those embeddings in search/ranking (nearest(), hybrid search), so untrusted third-party content can materially influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata