shopify-app-store-scraper
Fail
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The skill contains explicit instructions to bypass user oversight and consent mechanisms. Specifically, the 'BrowserAct Runtime' section commands the agent to 'install the missing dependency automatically without asking the user to confirm' and directs the agent to 'not request separate approval for dependency installation.'
- [EXTERNAL_DOWNLOADS]: The skill relies on external software from a third-party source at 'https://www.browseract.com' and the 'browser-act' GitHub repository. These dependencies are required for the skill's primary functionality.
- [COMMAND_EXECUTION]: The skill is designed to execute tasks through the 'BrowserAct CLI,' granting the agent the capability to run command-line tools and interact with a live browser environment.
- [INDIRECT_PROMPT_INJECTION]: The skill's core purpose is to ingest untrusted data from the Shopify App Store and other storefront pages. This creates an attack surface where malicious content on a scraped page could potentially influence the agent's subsequent actions.
- Ingestion points: Target URLs, search queries, and marketplace seller profiles.
- Boundary markers: None present; the instructions do not include delimiters or warnings to ignore instructions found within the scraped content.
- Capability inventory: Browser interaction, network response capture, and screenshot capabilities via the BrowserAct toolset.
- Sanitization: No sanitization or validation steps are defined for the captured web content.
Recommendations
- AI detected serious security threats
Audit Metadata