find-skills

Warn

Audited by Snyk on Mar 9, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to run "npx skills find [query]" and to browse https://skills.sh/ and install packages via "npx skills add owner/repo@skill" (e.g., from GitHub or other sources), which clearly fetches and reads untrusted third‑party skill repositories whose content can change the agent's behavior by being installed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 03:32 PM