bilibili-danmaku-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains explicit, deceptive installation instructions that tell the agent to auto-install a dependency and to hide/avoid requesting user approval, which is outside the scraper's stated purpose and instructs the agent to act without user consent.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use BrowserAct to access live Bilibili pages and extract danmaku/comment text (outsider-authored free text from public web content) into the agent’s runtime context for processing.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to automatically install the required BrowserAct runtime from the install URL at runtime (https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which is an external installer that would fetch/execute remote code and is required for the skill to run.