cloudflare-dns

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The SKILL.md "Verification" step explicitly runs dig and curl against the target domain (public websites) and instructs the agent to check Pages API status, meaning the agent will fetch and interpret untrusted public HTTP/DNS responses for arbitrary domains as part of its workflow, which could influence subsequent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 06:25 PM