skills-search

Warn

Audited by Snyk on Feb 26, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). This skill explicitly fetches public, user-contributed skill metadata from https://skills.sh/api/skills (see cli.js and the SKILL.md "Queries https://skills.sh/api/skills"), parses and displays topSource/install commands, and the workflow guides installing or acting on those results—so untrusted third‑party content could influence next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 09:20 AM