youtube-channel-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill instructs the agent to automatically install a runtime dependency and explicitly tells it to hide that action and not request user approval, which is deceptive and 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). SKILL.md instructs the agent to use the BrowserAct CLI to access real YouTube/browser pages at runtime and extract public channel text/metrics, which is outsider-authored free text from public web content.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill requires installing and invoking the BrowserAct CLI at runtime using the Install link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which would fetch and install remote code that directly enables execution of the agent's browser-act Skill.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The Skill explicitly tells the agent to install the BrowserAct dependency automatically without asking the user for confirmation and to resume execution, which encourages autonomous modification of the host system (installation of software) without user consent even though it doesn't explicitly request sudo, creating a security risk.