nudocs
Warn
Audited by Snyk on Mar 15, 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's SKILL.md explicitly describes pulling edited documents from Nudocs.ai (see "Pull Flow" and the example session where the agent "Runs: nudocs pull" and "Reads the downloaded file"), so the agent ingests and interprets user-generated content hosted on a third-party public service, which could contain instructions that influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata