ecommerce-new-arrivals-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill explicitly instructs the agent to automatically install a dependency without asking the user and to avoid describing or seeking approval for that installation, which is deceptive and outside the advertised monitoring purpose.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The Skill instructs automatic, non-consensual installation of an external CLI and directs capturing browser-visible network responses (which can include sensitive tokens), creating a supply-chain/installation abuse risk and potential exfiltration channel.

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 runtime browser-act Skill to “capture browser-visible page content” from user-specified target URLs/pages, which are outsider-authored web content and can include free-text prompt-injection payloads.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent at runtime to automatically install and invoke BrowserAct using the external installer links (https://www.browseract.com/?co-from=ecommerce and https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main), which would fetch and install/execute external code as a required runtime dependency.