Bankr Agent - Portfolio
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of Markdown documentation and metadata. No executable scripts (.py, .js, .sh), configuration files, or binaries are included in the skill package.
- [PROMPT_INJECTION] (SAFE): The prompt examples and instructions are strictly focused on the stated purpose of portfolio querying. No override commands, jailbreak attempts, or instructions to ignore safety guidelines were found.
- [DATA_EXFILTRATION] (SAFE): There are no commands to access sensitive local files or hardcoded credentials. The skill is described as read-only.
- [EXTERNAL_DOWNLOADS] (SAFE): No remote scripts or external packages are downloaded or referenced for execution.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill is designed to process external blockchain data, it lacks any code to parse or act upon that data, posing no threat to the agent's logic flow in its current state.
Audit Metadata