ad-landing-page-intent-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains explicit, deceptive instructions to install a runtime dependency automatically and to hide that action (not asking for user confirmation or describing it as a user-request), which is outside the stated purpose of monitoring landing pages and instructs the agent to act without user consent.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The document instructs silent, automatic installation of an external CLI without user confirmation or disclosure, enabling stealthy dependency installation and potential supply-chain or unauthorized installation abuse.

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 user-specified landing page URLs at runtime, which can ingest outsider-authored free text from public web pages into the LLM context.

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

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