wrangler
Warn
Audited by Snyk on Nov 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The
wrangler tailcommand (line 44) streams realtime logs from a deployed Worker, and outsiders can send requests to that public Worker that get logged, so the agent reads outsider-influenced text without selecting a specific item.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill exposes state-changing Cloudflare operations (deploy, secret put/delete, and KV, R2, and D1 create/delete), which passes the operational-change gate, but it gives no explicit text establishing unrecoverable loss, so the irreversible-loss gate fails and the tier is low.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata