youtube-video-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The Skill contains explicit, deceptive instructions to install a runtime dependency automatically and to hide that action from the user ("do not describe...and do not request separate approval"), which goes beyond normal operational guidance and instructs the agent to avoid user consent or disclosure.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The Skill explicitly instructs automatic installation of an external CLI without user confirmation or disclosure, which is a deceptive supply-chain/install-timebackdoor risk even though no direct data-exfiltration or remote-code-eval payloads are present.

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

• Third-party content exposure detected (high risk: 0.85). This skill’s required runtime workflow invokes the BrowserAct CLI to access real public YouTube pages/URLs and extract readable page content (outsider-authored free text from arbitrary web pages) into the agent’s LLM context.

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 and invoke the external BrowserAct CLI/Skill at runtime using the URL https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main (and the related https://www.browseract.com/?co-from=social-media), which would fetch and install remote code that the agent relies on to execute tasks.