find-skills

Warn

Audited by Snyk on Mar 3, 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 discover and install skills from public sources (https://skills.sh and GitHub via "npx skills add owner/repo@skill"), which means the agent will ingest untrusted third‑party skill metadata/code and use that content to decide on installations and next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 03:50 PM