hermesclaw-wechat-multi-agent

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow involves a proxy service that monitors and consumes messages from WeChat via the iLink API, where outsiders can submit free text messages that are directly ingested and queued for the agent.

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

• Potentially malicious external URL detected (high risk: 0.70). The installation instructions instruct the agent to run an external shell script fetched via curl from an arbitrary GitHub repository (https://raw.githubusercontent.com/AaronWong1999/hermesclaw/main/install.sh), constituting a weak/unknown/suspicious operational dependency.