obsidian-knowledge

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: 0.90). The skill's Intent Router explicitly accepts user-provided webpage URLs and delegates to the defuddle skill (with WebFetch as a fallback) to fetch and parse page content, then analyzes that content and may save or act on it (e.g., append to daily notes or save full-page WebClips), which exposes the agent to untrusted third‑party webpages (see "Intent Router" and Step 1–3 in SKILL.md).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 15, 2026, 06:10 AM
Issues
1