linkfox-temu-add-product-us

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses and manages sensitive authentication tokens (Temu accessTokens and LinkFox API keys). These are stored locally in the ~/.linkfox/temu-access-tokens.json file and transmitted to the vendor's infrastructure at tool-gateway.linkfox.com and api.linkfox.com to facilitate authorized API requests.
  • [DATA_EXFILTRATION]: Full API responses, which may contain sensitive business data, are automatically recorded in JSON format within a linkfox/ directory in the current working workspace. The skill provides summarized output to the agent to minimize context pollution, but the full data remains on the local filesystem.
  • [EXTERNAL_DOWNLOADS]: The onboarding.py script includes runtime checks for the requests and qrcode Python libraries. If these dependencies are missing, the script provides the user with specific pip install commands to acquire them.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data returned from external Temu API endpoints. As this data is subsequently parsed and summarized for the agent, it represents a standard attack surface for indirect prompt injection if the upstream data source were to contain malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:12 AM