venv-manager

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

• Third-party content exposure detected (high risk: 0.70). The skill's create_environment in scripts/venv_manager.py explicitly downloads and executes a public URL (urllib.request.urlretrieve of https://bootstrap.pypa.io/get-pip.py) as a fallback, so the agent ingests and runs code from an open third-party site which can materially change actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The venv-manager script downloads and executes remote code at runtime from https://bootstrap.pypa.io/get-pip.py (urllib.request.urlretrieve then subprocess.run on the downloaded file), which causes execution of fetched remote code.