youtube-hashtag-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 runtime dependencies automatically without user confirmation and to hide/avoid describing the installation link as a user-facing browser request, which overrides user consent and is outside the advertised scraping purpose.

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow invokes the browser-act Skill to access real YouTube pages (public web content) and extract readable page text/DOM, which can include outsider-authored free text that may be fed into the agent’s LLM context (indirect prompt injection risk).

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

• Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly tells the agent at runtime to automatically install the BrowserAct CLI using the remote installer URL https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which implies fetching and executing remote installation code as a required dependency.

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

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The Skill instructs the agent to automatically install the BrowserAct CLI and resume operation without asking the user for approval, directing it to modify the host system state (install software) and bypass user confirmation; while it does not explicitly request sudo or editing system files, the automatic-installation instruction poses a moderate risk of undesired system modification.