bind-utils

Warn

Audited by Snyk on Mar 18, 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's required workflow uses dig/nslookup/host to query arbitrary public domains and DNS records (see SKILL.md and references/cheatsheet.md examples like "dig TXT _dmarc.example.com +short" and "dig @8.8.8.8 example.com"), which means the agent will fetch and interpret untrusted, user-controlled third‑party DNS/content that can materially influence its diagnostic decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 01:37 PM
Issues
1