agentaudit-skill

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: 1.00). The skill's SKILL.md and audit prompt explicitly instruct the agent to query the public trust registry (https://agentaudit.dev) and to download and "read all files" from public sources (npm/pip packages, GitHub repos via git clone / npm pack / pip download) for LLM-powered audits, so untrusted, user-generated third‑party content is fetched and directly interpreted to drive PASS/WARN/BLOCK decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 06:59 AM