wechat-rpa-bot

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to ask the user for an Activation Code and then submit that code verbatim in a POST /api/license/activate JSON payload, which requires the LLM to handle and output a secret value directly.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). The GitHub repo/releases from "LeoMusk" deliver a zip that contains a Windows executable (service.exe) and the instructions recommend downloading and running it — distributing unsigned executables from an account that may be unverified is a high-risk delivery vector for malware.

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

• Potentially malicious external URL detected (high risk: 0.90). I flagged the GitHub release and repo URLs because the skill instructs the agent at runtime to download and unpack a release ZIP (https://github.com/LeoMusk/wechat-rpa-bot-skill/releases/download/v1.7.9/service-v1.7.9.zip) and/or git-clone the repo (https://github.com/LeoMusk/wechat-rpa-bot-skill.git), which fetch remote executable/source code that the installer/start scripts then run — a required runtime dependency that executes remote code.