youtube-comment-lead-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill instructs the agent to install a runtime dependency automatically and to conceal that action from the user ("without asking the user to confirm" and "do not describe it as a request..."), which are deceptive instructions outside the stated scraping purpose.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required workflow invokes the browser-act Skill to access and interact with live public YouTube pages at runtime, which can cause the agent to ingest outsider-authored free text from those pages (e.g., channel/about/video/comment content) into the LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The Skill explicitly requires and will automatically invoke the BrowserAct CLI/Skill and, if missing, instructs the agent to install it at runtime from https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main (and references https://www.browseract.com/?co-from=lead-generation), which means remote code/content fetched from those URLs would be executed and used as a required runtime dependency.