linkfox-amazon-store-fba

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill uses subprocess.run to execute a local verification script (check_auth_dependency.py) to confirm that the required linkfox-amazon-store-auth skill is present in the environment. This is a functional requirement for coordinating authentication across the vendor's skill suite.\n- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill communicates with vendor-managed domains (e.g., tool-gateway.linkfox.com, api.linkfox.com, agent-api.linkfox.com) to proxy SP-API requests and facilitate account onboarding. It also stores session data and full API responses in a local linkfox/ directory to provide context for the AI agent.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external Amazon SP-API calls, which serves as a potential surface for indirect prompt injection.\n
  • Ingestion points: Data enters the context via the payload field returned by the vendor proxy in scripts/_fba_runner.py.\n
  • Boundary markers: None identified; data is treated as structured JSON.\n
  • Capability inventory: The skill possesses capabilities for network operations (via urllib and requests) and local file system writes (session logging).\n
  • Sanitization: External data is parsed using standard JSON deserialization (json.loads).
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 03:04 PM
Security Audit — agent-trust-hub — linkfox-amazon-store-fba