link-understanding
Warn
Audited by Snyk on Mar 1, 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 explicitly calls understandLink(url) to fetch and analyze arbitrary web pages (e.g., examples and options like followInternalLinks, link graph analysis, and research/fact-check workflows that call understandLink on search results), so the agent will ingest untrusted public third-party content which can influence subsequent decisions and actions.
Audit Metadata