sanctum

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, or unauthorized data exfiltration were detected. The skill's behavior aligns with its stated purpose of providing DeFi integration tools.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with external APIs at sanctum-api.ironforge.network and sanctum-s-api.fly.dev to fetch token metadata and unsigned transaction data. These are legitimate endpoints for the Sanctum protocol, and the use of the Ironforge infrastructure provider is a standard practice in the Solana ecosystem.
  • [COMMAND_EXECUTION]: The skill provides code to sign and broadcast transactions to the Solana network. This is the primary intended purpose of the skill, and the implementation uses the well-known @solana/web3.js library. The logic is transparent and involves local signing of transactions fetched from the protocol API.
  • [CREDENTIALS_UNSAFE]: The skill correctly handles sensitive information by using environment variable placeholders (e.g., process.env.SOLANA_PRIVATE_KEY) in its templates and placeholders for API keys in its documentation, adhering to secret management best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 12:31 AM
Security Audit — agent-trust-hub — sanctum