uv

Warn

Audited by Snyk on Feb 15, 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 explicitly installs and runs third‑party packages from public package indexes (e.g., uv add, uv run --with ..., uv auth login / uv publish to PyPI), which pulls untrusted, user‑published code/artifacts that the agent may ingest or execute.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:55 PM