multi-copywrite-alchemy

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required workflow in references/core_workflow.md fetches article content and account details from external platform APIs (WeChat Official Accounts and Douyin) based on user-supplied account names or IDs at runtime.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs the agent to fetch remote API endpoints from https://redfox.hk/story/api/ at runtime using a user-supplied API key to retrieve article data and control the analysis workflow.