csp-bypass-advanced
Warn
Audited by Snyk on Nov 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill is static reference material, but its trick note directs the agent to run a web search (
site:googleapis.com inurl:callback) and to pull attacker-publishable CDN packages (jsdelivr/unpkg), so outsider-authored web content is reachable only through an active search or fetch and is not forced into a monitored feed.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata