financial-report-anomaly-question-list

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

• Potentially malicious external URL detected (high risk: 1.00). The provided runner (scripts/run.py) performs runtime POST requests to the external AI Skills API at https://ai-skills.ai (DEFAULT_BASE_URL) to execute the skill (/api/execute), so the skill relies on remote execution and the returned content directly controls the agent's behavior.