write-like-meng-on-x

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to open and fetch live posts from X at runtime (e.g., https://x.com/MengTo and https://x.com/search?q=from%3AMengTo&src=typed_query&f=live), and those fetched tweets are then ingested/used to directly shape prompts and the voice corpus.