skills/ton-org/kit/ton-proof/Gen Agent Trust Hub

ton-proof

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows the TonConnect protocol for wallet authentication and proof of ownership.\n- [COMMAND_EXECUTION]: The skill utilizes the generate_ton_proof and get_wallet tools to interact with the TON blockchain. These operations are required for the skill's functionality and are protected by a mandatory user confirmation step.\n- [PROMPT_INJECTION]: The skill handles untrusted data as part of the authentication flow.\n
  • Ingestion points: Workflow step 1 accepts domain and payload from users or external verifying services.\n
  • Boundary markers: No explicit delimiters are defined for input data in the instructions.\n
  • Capability inventory: The skill calls the generate_ton_proof tool to sign data.\n
  • Sanitization: Workflow step 2 explicitly prohibits modification of the input payload to maintain cryptographic integrity.\n
  • Mitigation: Workflow step 3 enforces a mandatory user confirmation before signature generation, mitigating the risk of automated or deceptive signing requests.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 09:50 AM
Security Audit — agent-trust-hub — ton-proof