ai-customer-journey-map

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

• Potentially malicious external URL detected (high risk: 0.80). scripts/run.py makes runtime POST requests to https://ai-skills.ai/api/execute (DEFAULT_BASE_URL / AISKILLS_BASE_URL) and thus relies on that external service to execute the skill logic and return instructions/results, meaning remote code/execution controls the agent output.