notebook-research

Warn

Audited by Snyk on Jul 17, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). SKILL.md describes a runtime workflow that can ingest outsider-authored free text via web research and URL-based sources (e.g., nlm research start ... / nlm research import ... and nlm source add ... --url ...), where fetched page text is then used for nlm notebook query.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 17, 2026, 01:14 PM
Issues
1