linkfox-temu-store-query

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEPERSISTENCEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PERSISTENCE]: The documentation in references/onboarding.md provides instructions to modify shell configuration files such as ~/.zshrc, ~/.bashrc, and ~/.bash_profile to store the LINKFOX_AGENT_API_KEY. This is intended to ensure the API key persists across terminal sessions.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process store data from the external Temu API, creating a potential surface for indirect prompt injection if the API returns adversarial content.
  • Ingestion points: External data enters the agent context via the output of scripts/temu_store_query.py.
  • Boundary markers: The scripts do not use explicit delimiters or instructions to ignore potential commands embedded in the API response.
  • Capability inventory: The skill has capabilities for network access, file writing, and command execution via the provided Python scripts.
  • Sanitization: There is no evidence of sanitization or filtering of the content received from the Temu API gateway before it is presented to the agent.
  • [COMMAND_EXECUTION]: The skill involves the execution of local Python scripts (scripts/onboarding.py, scripts/temu_store_query.py) that perform various tasks including network requests to vendor APIs, file system operations for session logging, and user authentication flows.
  • [EXTERNAL_DOWNLOADS]: The scripts/onboarding.py file prompts the user to install external Python packages (requests, qrcode, pillow) which are required for full functionality, such as generating payment QR codes and performing authenticated HTTP requests.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:56 AM