banking-compliance
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious code, obfuscation, or unauthorized data exfiltration patterns were found. The skill adheres to its stated purpose of banking regulatory assessment.
- [PROMPT_INJECTION]: The skill processes external data files such as CSV exposures for RWA calculations. This creates a theoretical indirect prompt injection surface, though no malicious instructions were identified in the provided files and the functionality is necessary for the skill's core purpose.
- [COMMAND_EXECUTION]: The skill facilitates the execution of a local script, calculate.py, to ensure mathematical accuracy in capital ratio computations. This script is limited to deterministic calculations and does not interact with the network or sensitive system files.
Audit Metadata