skills/bankrbot/skills/bankr/Gen Agent Trust Hub

bankr

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation instructs users to install the @bankr/cli package via npm or bun. This is a vendor-owned resource necessary for interacting with the Bankr API and performing the described operations.
  • [COMMAND_EXECUTION]: The skill utilizes a custom binary (bankr) to execute a wide range of tasks, such as managing crypto portfolios, signing transactions, and deploying tokens. These commands are the primary method of interaction for the skill's intended use cases.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is capable of browsing the web and extracting data from external pages and x402 API schemas. This functionality allows untrusted data to enter the agent's context, though this is a standard risk for agents with web-access capabilities.
  • [SAFE]: Configuration and sensitive API keys are managed using standard industry practices, including the use of .env files and a dedicated config directory (~/.bankr/), which the documentation correctly advises users to keep out of version control.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 01:11 PM
Security Audit — agent-trust-hub — bankr