temu-product-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 BrowserAct without user confirmation and explicitly tells the agent not to describe this as a user-facing request (i.e., to conceal and bypass user consent), which is a hidden/deceptive instruction 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 browser pages” and “capture browser-visible page content” from user-supplied target URLs at runtime, which can include outsider-authored free text from public web pages.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill directs the agent at runtime to automatically install and invoke the BrowserAct CLI from https://www.browseract.com/?co-from=ecommerce (and the installation redirect URL https://www.browseract.com/?co-from=ecommerce&redirect=https://github.com/browser-act/skills/tree/main), which fetches and executes remote code required for the skill to run.

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 directs the agent to install the BrowserAct CLI automatically and "obtain the required Skill" without asking the user or requesting approval, which encourages performing software installation and modifying the host system state without user consent.