skills/nanocoai/nanoclaw/add-imessage/Gen Agent Trust Hub

add-imessage

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local setup scripts (setup/channels/imessage-configure.sh, setup/lib/restart.sh) and uses pnpm to build and test the newly added iMessage adapter.
  • [DATA_EXFILTRATION]: For local integration on macOS, the skill is designed to access the user's iMessage database (chat.db). This is the primary purpose of the skill and requires a manual grant of 'Full Disk Access' by the user to the Node.js runtime.
  • [CREDENTIALS_UNSAFE]: The skill collects a Photon API key from the user for remote operations. This secret is passed as a command-line argument to a configuration script before being stored in a .env file. While standard for this setup, secrets in shell arguments can potentially be visible in system process lists.
  • [EXTERNAL_DOWNLOADS]: The skill installs the chat-adapter-imessage package and retrieves specific source files from an external git branch (channels) to implement the bridge functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 06:15 AM
Security Audit — agent-trust-hub — add-imessage