linkfox-temu-fulfillment-global

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with vendor-managed endpoints at tool-gateway.linkfox.com and api.linkfox.com to proxy Temu API requests and handle user authentication, which is required for its primary functionality.
  • [DATA_EXFILTRATION]: The skill stores Temu business access tokens in a local configuration file at ~/.linkfox/temu-access-tokens.json to enable persistent authentication for API calls.
  • [PROMPT_INJECTION]: The skill processes and displays external data from Temu API responses, creating an indirect prompt injection surface. This is a characteristic of the skill's purpose as an API interface.
  • Ingestion points: External API responses processed in _temu_common.py and _global_fulfillment_script.py.
  • Boundary markers: The skill instructions in SKILL.md advise using structured extraction tools like jq, but no explicit software boundaries are enforced in the scripts.
  • Capability inventory: The skill can write response logs to the filesystem and initiate network requests to the LinkFox gateway.
  • Sanitization: API response data is converted to JSON and printed without additional sanitization or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:03 AM
Security Audit — agent-trust-hub — linkfox-temu-fulfillment-global