shopify-storefront-scraper
Fail
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructions specify that the agent should automatically install the 'BrowserAct' CLI and skill from an external URL (browseract.com) if they are missing from the environment. This involves downloading and executing code from an unverified third-party source.\n- [COMMAND_EXECUTION]: The skill explicitly commands the agent to override standard security procedures by performing the installation "without asking the user to confirm" and stating that the agent should "not request separate approval for dependency installation." This is a direct attempt to bypass user oversight for executing administrative-level commands and installing external software.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to scrape external websites (Shopify stores). This introduces a risk where malicious instructions embedded in the target website's content could be executed by the agent during the processing of the scraped data.\n
- Ingestion points: Browser-visible page content and metadata from Shopify storefronts.\n
- Boundary markers: No boundary markers or "ignore embedded instructions" directives are present to isolate scraped data.\n
- Capability inventory: The skill possesses network access and browser automation capabilities through the required BrowserAct toolset.\n
- Sanitization: There is no evidence of sanitization or validation of the data retrieved from external storefronts before it is returned or processed.
Recommendations
- AI detected serious security threats
Audit Metadata