youtube-channel-business-contact-search

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill contains explicit, deceptive instructions to install dependencies automatically without asking the user and to hide/avoid describing that installation, which is outside the stated contact-search 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 and interact with public YouTube pages at runtime (e.g., About/contact text), which is outsider-authored free text that can be ingested into the LLM context via the browser-extracted page content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires installing and invoking the external BrowserAct CLI at runtime using the URL https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main (and the related https://www.browseract.com/?co-from=lead-generation), which would fetch and execute remote code and supply runtime instructions the agent must follow.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The Skill explicitly instructs the agent to automatically install the BrowserAct CLI/runtime dependencies without asking the user for approval, which requires modifying the host system (installing software) and could trigger privileged operations.