linkfox-shopee-store-ams

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The helper script _shopee_ams_common.py executes a local bundled dependency checker check_auth_dependency.py using subprocess.run. This operation is restricted to the skill's own internal directory and is used solely for environment validation.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with vendor-controlled domains including tool-gateway.linkfox.com, api.linkfox.com, and agent-api.linkfox.com for API proxying and user authentication. These interactions are legitimate communications with the developer's infrastructure.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill ingests data from Shopee API responses through the _ams_api_runner.py script.
  • Boundary markers: Not explicitly defined in the execution flow.
  • Capability inventory: File writing, network communication, and restricted local command execution.
  • Sanitization: External data is processed using standard JSON parsing, which mitigates simple injection risks, although no specific LLM-targeted sanitization is present.
  • [DATA_EXFILTRATION]: The skill transmits the LINKFOX_AGENT_API_KEY to the vendor's gateway to authenticate requests. This transmission is a documented functional requirement for the skill to interact with the Shopee platform on the user's behalf.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 07:03 AM
Security Audit — agent-trust-hub — linkfox-shopee-store-ams