ml-verify

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's Web mode explicitly mandates WebFetch of external docs at runtime and to quote exact values into the agent's findings (e.g., https://huggingface.co/docs/peft/main/en/conceptual_guides/lora), so fetched pages directly control the agent's prompts/output and are a required runtime dependency.