linkfox-temu-compliance-global

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes and displays data fetched from external Temu API endpoints via the LinkFox gateway. Maliciously crafted data from these external sources could potentially contain instructions that influence the agent's behavior.
  • Ingestion points: The call_temu_api function in scripts/_temu_common.py retrieves data from the tool gateway.
  • Boundary markers: The skill does not employ specific delimiters or instructions to the agent to ignore potentially malicious content within the API responses.
  • Capability inventory: The skill has filesystem write capabilities (saving responses to the linkfox/ directory) and network access.
  • Sanitization: No sanitization or filtering of the external API data is performed before it is provided to the agent context.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill manages sensitive Temu access tokens by storing them locally in ~/.linkfox/temu-access-tokens.json. While this is a functional requirement for persisting shop authorization, it stores credentials in plain text on the local filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:03 AM
Security Audit — agent-trust-hub — linkfox-temu-compliance-global