fnos-cli

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The bootstrap scripts download the fnos-cli binary from the author's GitHub repository and npmmirror. The process is secured by multi-stage SHA-256 integrity verification against hardcoded hashes.
  • [REMOTE_CODE_EXECUTION]: The skill uses a download-and-execute pattern for its core CLI tool. This is intended behavior and is protected by hash verification.
  • [DYNAMIC_EXECUTION]: The bootstrap scripts prepare and launch a native binary downloaded at runtime.
  • [COMMAND_EXECUTION]: Executes native binary commands for device management. High-risk operations (e.g., storage formatting, SSH toggling, system power control) require explicit user confirmation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted device data (file lists, log entries) and possesses destructive system-level capabilities.
  • Ingestion points: Device API responses processed by modules like file, log, and photos.
  • Boundary markers: Commands are wrapped in a native CLI with argument isolation.
  • Capability inventory: File system modification, user management, Docker control, and system power management.
  • Sanitization: Relies on the CLI's internal handling of structured input and output.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 11:29 AM