creator-commercial-value-benchmark

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

• Potentially malicious external URL detected (high risk: 1.00). The provided runner calls the external endpoint https://ai-skills.ai/api/execute (DEFAULT_BASE_URL) at runtime and depends on that service (via AISKILLS_API_KEY) to execute the skill and produce prompts/responses, so remote content controls execution.