made-in-china-search-results-scraper

Warn

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions require the agent to download the 'BrowserAct' CLI from an external domain (browseract.com) if the tool is not already installed on the system.
  • [REMOTE_CODE_EXECUTION]: The skill contains explicit instructions to 'install the missing dependency automatically without asking the user to confirm' and further mandates that the agent 'do not request separate approval for dependency installation.' This bypasses user consent and security oversight for the execution of installation scripts or binaries from an unverified external source.
  • [COMMAND_EXECUTION]: The skill relies on the execution of a Command Line Interface (CLI) tool ('browser-act') to perform its primary functions, which involves spawning subprocesses to interact with a web browser.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external websites.
  • Ingestion points: Browser-visible page content and network responses from 'Made-in-China' search results (SKILL.md, Step 5).
  • Boundary markers: None specified in the instructions to separate external data from system instructions.
  • Capability inventory: The agent has the ability to execute shell commands via the BrowserAct CLI and access the file system within the workspaces/ directory.
  • Sanitization: No mention of validation, escaping, or filtering of the scraped content before it is returned or processed.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 20, 2026, 04:14 AM
Security Audit — agent-trust-hub — made-in-china-search-results-scraper