blockrun

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of an external Python package blockrun-llm via pip to function. This package acts as the SDK for interacting with the BlockRun micropayment and routing platform.
  • [COMMAND_EXECUTION]: The skill provides Python code snippets for the agent to execute, including initializing a wallet, checking balances, and routing chat requests to various external models (OpenAI, xAI, Google, DeepSeek).
  • [DATA_EXFILTRATION]: While the skill communicates with external APIs to process prompts and retrieve search results/images, this is the intended primary purpose of the skill (acting as a proxy for premium AI services). It does not appear to access or send sensitive local files such as SSH keys or environment variables.
  • [CREDENTIALS_UNSAFE]: The skill uses an 'agent wallet' model for authentication and payments, explicitly stating that no API keys are needed. It manages a local session file at $HOME/.blockrun/.session to store wallet state, which is a standard practice for this type of service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 11:55 AM
Security Audit — agent-trust-hub — blockrun