lark-workflow-meeting-summary

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

• Potentially malicious external URL detected (high risk: 0.80). The runner (scripts/run.py) makes runtime POST requests to the external API at https://ai-skills.ai/api/execute (via DEFAULT_BASE_URL or AISKILLS_BASE_URL) which executes the skill remotely and returns instructions/results, so this external URL is a required runtime dependency that effectively executes remote code and controls agent behavior.