project-setup

Warn

Audited by Snyk on Mar 10, 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). The SKILL.md workflow explicitly instructs (Workflow step 2) to perform a WebSearch for "[language] project setup best practices" and then "Follow setup", which requires fetching and interpreting open/public third‑party web content that can change the agent's setup actions.

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill includes a setup command that runs "curl -LsSf https://astral.sh/uv/install.sh | sh", which downloads and executes remote code at runtime (and the .pre-commit-config also pulls https://github.com/astral-sh/ruff-pre-commit during pre-commit installation), so these are required runtime fetches that execute external code.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 02:24 AM