wechat-mp-exporter

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). Several URLs point to off-origin/hostile domains, authority-typos/quasi-subdomains, credential-bearing authorities, or an unfamiliar GitHub repo — all indicators of potentially malicious, typosquatting, or otherwise untrusted download sources.

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

• Third-party content exposure detected (medium risk: 0.30). In Lite mode, the runtime fetches and parses outsider-authored article HTML from https://mp.weixin.qq.com/ (e.g., content_html and extract_content in scripts/lite_backend.py), which is free text authored by external users/WeChat accounts.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill declares and uses the upstream git repository https://github.com/wechat-article/wechat-article-exporter.git (UPSTREAM_URL) as a runtime fetch for Docker onboarding/build, which pulls remote code that is later built/executed—so this is a runtime external dependency that executes remote code.