search-aliexpress
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [DYNAMIC_EXECUTION]: The skill utilizes Playwright to automate browser interactions, including clicking DOM elements and executing JavaScript snippets for data extraction. These operations are limited to the context of the target website's DOM and are used for legitimate automation of the search process.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill communicates with AliExpress (
he.aliexpress.com), which is a well-known e-commerce service. It performs network operations to retrieve product listings and manages cookies (aep_usuc_f,xman_us_f) specifically to set the user's currency to ILS and locale to Hebrew. These operations are essential for the skill's purpose and target a recognized domain. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by scraping product titles and badges directly from AliExpress search results.
- Ingestion points: Product card titles, prices, and badges extracted from the
he.aliexpress.comresults page. - Boundary markers: The extraction logic does not include delimiters or instructions to the agent to disregard potential instructions embedded in the scraped text.
- Capability inventory: The skill uses Playwright to control a browser, which includes the ability to navigate to other URLs and execute JavaScript.
- Sanitization: The extraction script reads and returns raw text from the DOM without performing sanitization or filtering for malicious patterns.
Audit Metadata