llm-wiki
Warn
Audited by Snyk on May 14, 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.md ingest workflow explicitly auto-fetches and extracts content from arbitrary public URLs (via adapters like baoyu-url-to-markdown, wechat-article-to-markdown, youtube-transcript) and requires the agent to read/structure that third‑party content (Step 1 JSON analysis → Step 2 page generation), so untrusted web/social media content can directly influence downstream decisions and actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata