cli-anything

Warn

Audited by Snyk on Apr 1, 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 workflow explicitly accepts and clones public GitHub URLs as source (Phase 1 "Source Acquisition" and examples like "/cli-anything https://github.com/blender/blender" in SKILL.md), then analyzes that untrusted repository code (Phase 2 "Codebase Analysis") to drive CLI generation, so third-party content can directly influence agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 1, 2026, 08:29 PM
Issues
1