fujitsu-mainframe
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- 4. Unverifiable Dependencies & Remote Code Execution (SAFE): The skill utilizes the standard 'find' utility to search for source files locally. No remote scripts are downloaded or executed.
- 8. Indirect Prompt Injection (SAFE): The skill analyzes external legacy code which could contain malicious instructions.
- Ingestion points: Local filesystem access for COBOL, JCL, and configuration files.
- Boundary markers: Absent in the current prompt instructions.
- Capability inventory: File discovery and code generation.
- Sanitization: No content filtering of analyzed source files is mentioned.
Audit Metadata