surf-codebase
Warn
Audited by Snyk on Feb 16, 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's content scripts and CDP operations (e.g., the READ_PAGE/GENERATE_ACCESSIBILITY_TREE handler in src/content/accessibility-tree.ts, getResponseBody/getNetworkRequests in src/cdp/controller.ts, and Network.* event capture) ingest and expose arbitrary web page and network content from public/third-party URLs for the agent to read and act on, which can include untrusted user-generated content.
Audit Metadata