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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 05:19 PM
Issues
1