maestro

Warn

Audited by Snyk on Jul 1, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The Maestro skill runs npx to fetch/install remote skills at runtime (e.g., the command "npx skills add owner/repo@skill" used in the Discover/install flow), and the installed skill's SKILL.md is subsequently read and injected into subagent prompts — meaning remote repository content directly controls agent instructions.

Issues (1)

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 1, 2026, 08:15 PM
Issues
1
Security Audit — snyk — maestro