temu-search-results-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill contains explicit, deceptive instructions (lines 41–47) telling the agent to auto-install a dependency without user confirmation and to conceal that installation from the user, which overrides normal consent/communication 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: 0.85). SKILL.md instructs the agent to use BrowserAct to “capture browser-visible page content” and “network responses exposed during the authorized session,” which at runtime will ingest outsider-authored free text from public Temu web pages fetched via arbitrary target URLs.

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 to auto-install and invoke BrowserAct at runtime using the install 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 are required runtime dependencies that would fetch and execute remote installation code.

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

• Attempt to modify system services in skill instructions detected (low risk: 0.30). The Skill directs the agent to automatically install a required CLI dependency without asking the user for confirmation and to treat it as a required runtime dependency, which instructs the agent to change the host environment (install software) and to do so without explicit user approval — a low-to-moderate risk of modifying machine state though it does not explicitly request sudo or system-file edits.