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_apifunction inscripts/_temu_common.pyretrieves 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