update-claude

Warn

Audited by Snyk on Mar 13, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.80). I flag the remote package installs referenced by the skill—specifically "npm install -g @anthropic-ai/claude-code@latest" (which downloads/installs code from the npm registry) and the installer invoked by "npx skills add amu815/update-claude-skill"—because both fetch and execute remote code at install/runtime and the skill relies on those external packages.

Issues (1)

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 13, 2026, 06:41 AM
Issues
1