dig
Warn
Audited by Snyk on Mar 7, 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.md explicitly instructs the agent to query public DNS data (e.g., "dig TXT", "dig axfr", and propagation checks against public resolvers like @8.8.8.8") which fetches untrusted, user-published DNS records that the agent must read/interpret and that can materially affect subsequent actions (e.g., follow-up probing based on AXFR/subdomain discovery).
Audit Metadata