search-skills

Fail

Audited by Snyk on Jun 24, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.90). This is a raw GitHub URL pointing to an install.sh intended to be run (curl | sh) from an unverified/unknown GitHub user — a high-risk pattern because it executes remote code and can easily deliver malware.

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

  • Third-party content exposure detected (medium risk: 0.65). The runtime workflow uses skit search <query> and then presents/installs a “source” from search results; since skit search typically fetches public/community registry or web content to produce those results, the LLM may ingest outsider-authored free text (e.g., skill names/descriptions) from those public sources.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime install command that fetches and pipes a remote shell script into sh (curl -fsSL https://raw.githubusercontent.com/vlln/skit/main/install.sh | sh), which would execute remote code at runtime and is relied on to install the required 'skit' tool.

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
Jun 24, 2026, 11:05 AM
Issues
3
Security Audit — snyk — search-skills