weibo-hot-search-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill instructs the agent to automatically install a missing CLI dependency from an external link without user confirmation, which weakens user control over environment execution.

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

• Third-party content exposure detected (low risk: 0.10). The workflow scrapes Weibo hot search rankings and public social media pages via browser extraction, which exposes the agent to outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to automatically download and install a runtime skill package from an unverified third-party GitHub repository (https://github.com/browser-act/skills/tree/main), presenting a weak/unknown provenance operational dependency.