skills/ton-org/skills/ton-cli/Gen Agent Trust Hub

ton-cli

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute commands using npx @ton/mcp@alpha. This is the core mechanism for providing raw CLI access to TON wallet tools.
  • [EXTERNAL_DOWNLOADS]: The skill invokes npx to download and run the @ton/mcp package from the official NPM registry. The package belongs to the vendor ton-org, matching the skill author's organization.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect injection by ingesting untrusted data from the TON blockchain (e.g., transaction data, DNS records, jetton metadata).
  • Ingestion points: Tools such as get_transactions, resolve_dns, and get_jettons fetch external data into the agent's context.
  • Capability inventory: The skill has the capability to write to the blockchain and execute shell commands via Bash.
  • Boundary markers: The instructions include a strict requirement for the agent to "Always confirm with the user before running" sensitive transaction tools.
  • Sanitization: The tool output is structured as JSON, which helps prevent the agent from misinterpreting blockchain data as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 09:38 AM