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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata