temu-category-listing-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the agent to download and install the 'BrowserAct CLI' and a related agent skill from an external domain (browseract.com) and an unverified GitHub repository.
- [REMOTE_CODE_EXECUTION]: The skill directs the agent to use an installation link to obtain missing dependencies automatically. This pattern facilitates the download and execution of external code on the user's environment.
- [COMMAND_EXECUTION]: The instructions explicitly command the agent to perform installations "automatically without asking the user to confirm," which constitutes unverified execution of setup scripts on the host system without user oversight.
- [PROMPT_INJECTION]: The skill instructs the agent to bypass security protocols by stating "do not request separate approval for dependency installation" and directing the agent to avoid describing the process to the user. This is an attempt to override the agent's safety constraints regarding software installation and user consent.
Recommendations
- AI detected serious security threats
Audit Metadata