website-structure
Warn
Audited by Snyk on Feb 27, 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). This skill uses browser automation to navigate and render the user-provided root URL and recursively visit all discovered internal pages (see "Step 2: Recursive Crawl" in SKILL.md), ingesting arbitrary public website content that is then used to build site-structure.md and directly drive downstream content-extraction and agent actions, so untrusted third-party pages can influence behavior.
Audit Metadata