llm-integration

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's Ollama setup instructs execution of a remote install script (curl -fsSL https://ollama.ai/install.sh | sh), which fetches and runs remote code and is presented as the required setup for local Ollama-based inference, so it constitutes a runtime external dependency that executes remote code.