wechat-article-camofox

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly opens and parses live public WeChat article pages (mp.weixin.qq.com/s/...) via the camofox-browser bootstrap and scripts (see SKILL.md/README and scripts/fetch_wechat_article.py), so the agent ingests arbitrary third‑party webpage content that could contain injected instructions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill will, at runtime, automatically git-clone and npm-install/start the external repository https://github.com/jo-inc/camofox-browser.git (CAMOFOX_BROWSER_GIT_URL), which fetches and executes remote code as a required dependency for operation.