ov-server-operate

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes config templates and explicitly instructs replacing placeholders with real API keys/root_api_key and to ask users for keys, which encourages the agent to receive and insert secrets verbatim into config files (and thus output them), creating an exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). Most URLs are local or API endpoints and not risky, but the direct download of a shell installer from an external/unvetted domain (https://astral.sh/uv/install.sh) is high risk because piping/running remote .sh files can execute arbitrary code and is a common malware distribution vector.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime installation step that fetches and executes remote code via curl -LsSf https://astral.sh/uv/install.sh | sh, which runs arbitrary remote script and is a required dependency for subsequent steps (uv venv / uv pip), so it is a high-confidence risky external dependency.