product-changelog
Warn
Audited by Snyk on Mar 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The SKILL.md "Generating Visuals" section explicitly instructs running infsh/agent-browser with an arbitrary URL (e.g., "https://your-app.com/new-feature") to fetch/screenshot live web pages, so the agent would ingest untrusted public web content that can influence outputs.
Audit Metadata