temu-product-scraper

Warn

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: MEDIUMPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill includes instructions to install dependencies 'automatically without asking the user to confirm' and specifically directs the agent to 'do not request separate approval for dependency installation.' This represents a direct attempt to override standard agent control mechanisms and user oversight regarding high-risk actions like software installation.
  • [EXTERNAL_DOWNLOADS]: The instructions require the agent to fetch and install software from an external domain (browseract.com) that is not a recognized or trusted service provider.
  • [COMMAND_EXECUTION]: The skill's primary functionality relies on the execution of an external CLI tool ('browser-act') that is downloaded and installed at runtime from an untrusted source.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection: 1. Ingestion points: The skill processes untrusted web data from Temu product pages (SKILL.md). 2. Boundary markers: No delimiters or ignore instructions are present to protect the agent from embedded malicious content. 3. Capability inventory: The agent has the capability to execute the 'browser-act' CLI tool and perform web interactions. 4. Sanitization: There is no logic provided to sanitize or validate the external data before it enters the agent's context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 20, 2026, 04:20 AM
Security Audit — agent-trust-hub — temu-product-scraper