setup-agentpw
Warn
Audited by Snyk on Apr 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's documentation (references/patterns.md, "Pattern 4: Proxy pattern — classify upstream 401s") explicitly fetches arbitrary targetUrl responses and passes the upstream HTTP response into pw.connect.classifyResponse and pw.connect.prepare, meaning untrusted third-party HTTP content is read and can influence connection flows and subsequent agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata