skills/makerjackie/skills/mj-cf-dns/Gen Agent Trust Hub

mj-cf-dns

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a 'verify before write' workflow. It enforces rules in SKILL.md requiring the agent to list existing records before modification and to default to dry-run plans unless explicitly overridden by the user.
  • [SAFE]: Credential management follows best practices. Instructions explicitly forbid the agent from printing API tokens, only allowing it to report their presence. The helper script scripts/mj-cf-dns.mjs consumes these credentials directly from environment variables.
  • [SAFE]: Command execution is handled securely. The script uses execFileSync to invoke the dig utility for DNS verification. By passing arguments as an array and avoiding the shell, it prevents command injection vulnerabilities.
  • [SAFE]: Network operations are restricted to the official Cloudflare API (api.cloudflare.com). No evidence of data exfiltration or communication with suspicious third-party domains was found.
  • [SAFE]: Dependency usage is standard for the described purpose. The skill utilizes npx wrangler, which is the official tool for Cloudflare Workers, and standard Node.js built-ins.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 07:50 AM
Security Audit — agent-trust-hub — mj-cf-dns