Bankr Agent - Token Trading
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No patterns of instruction override, safety bypass, or role-play jailbreaks were detected in the skill instructions.
- [Data Exposure & Exfiltration] (SAFE): The skill lacks any scripts or logic that could access the file system or perform unauthorized network requests.
- [Remote Code Execution] (SAFE): No mechanisms for downloading or executing remote code were found.
- [Command Execution] (SAFE): There are no subprocess calls or system-level commands within the provided content.
- [Indirect Prompt Injection] (LOW): While the skill defines how to process user trading queries, it does not include logic for ingesting or rendering untrusted external data (e.g., web scraping or API results) that could trigger downstream exploits.
- [No Code] (INFO): This skill is composed solely of markdown documentation (SKILL.md) and provides guidance to the AI agent rather than functional code.
Audit Metadata