find-skills

Fail

Audited by Snyk on Jul 2, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.80). skillhu.bz appears to be an instant-publish skills marketplace with no auth and direct install capabilities (npx/install), meaning it can distribute arbitrary code or installers from an unvetted source and therefore represents a higher risk unless each package is verified.

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

  • Third-party content exposure detected (high risk: 0.85). The runtime workflow runs npx skillhu search and npx skills find against public/community marketplaces, which can return outsider-authored skill metadata/descriptions that the agent then ingests into its LLM context when presenting results to the user.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill instructs running npx to fetch and execute remote packages (e.g., "npx skillhu" / "npx skills add") and to install GitHub repo-based skills (e.g., vercel-labs/agent-skills@...) from the marketplaces (https://skillhu.bz and https://skills.sh), which are runtime downloads that execute remote code.

Issues (3)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Jul 2, 2026, 07:10 PM
Issues
3
Security Audit — snyk — find-skills