ecommerce-product-feed-audit
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that direct the agent to override standard safety procedures by installing dependencies 'automatically without asking the user to confirm' and explicitly telling the agent to 'not request separate approval for dependency installation.'
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to download and install a software dependency from an external domain (
www.browseract.com). - [REMOTE_CODE_EXECUTION]: The requirement for 'automatic' installation of a CLI tool from a remote URL facilitates the execution of unverified code on the host system.
- [COMMAND_EXECUTION]: The skill's operational logic depends on the execution of the
browser-actcommand-line interface to perform its primary tasks.
Recommendations
- AI detected serious security threats
Audit Metadata