wespy-fetcher

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

• Third-party content exposure detected (low risk: 0.10). The agent fetches and processes arbitrary external web pages and WeChat articles via URLs provided by the user, representing low-risk ingestion of outsider-authored content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill clones and executes code from an arbitrary personal GitHub repository (https://github.com/tianchangNorth/WeSpy.git) at runtime, which lacks strong official enterprise or foundational provenance and classifies as high risk.