geo-technical
Warn
Audited by Snyk on Jul 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: 0.85). SKILL.md instructs the runtime workflow to fetch arbitrary target URLs’ raw HTML/robots.txt/sitemaps via curl/WebFetch (outsider-authored web content), which is then analyzed and used to generate the audit in the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata