linkfox-temu-product-query
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEPERSISTENCECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PERSISTENCE]: The skill provides instructions in
references/onboarding.mdfor users to store their API keys by appending export commands to shell profile files (~/.zshrc,~/.bashrc) or using thesetxcommand on Windows. This is a standard practice for managing persistent environment variables for CLI tools. - [COMMAND_EXECUTION]: The skill utilizes local Python scripts,
scripts/temu_product_query.pyandscripts/onboarding.py, to interact with the Temu product API and handle user onboarding tasks like SMS verification and billing. These scripts are invoked via the command line as part of the skill's intended functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes product data from external Temu API responses, which presents a potential attack surface if the remote content contains malicious instructions intended for the agent.
- Ingestion points: API responses fetched from
ehunt/temu/productQueryinscripts/temu_product_query.py. - Boundary markers: No explicit delimiter or instruction-ignoring markers are used in the processing scripts.
- Capability inventory: The skill can execute local Python scripts and perform authenticated network operations to vendor-controlled domains.
- Sanitization: The scripts perform standard JSON parsing and data summarization but do not explicitly sanitize the text content for potential injection patterns.
Audit Metadata