risk-management-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, prompt injections, or security vulnerabilities were detected across the skill files.
- [COMMAND_EXECUTION]: The skill utilizes a local script
scripts/risk_matrix_calculator.pyfor risk level and FMEA RPN calculations. Technical review of the source code confirms it uses only standard Python libraries (argparse,json,sys) and performs purely mathematical logic without any dangerous system calls, file access, or network operations. - [DATA_EXPOSURE]: There are no hardcoded credentials, sensitive file paths, or network exfiltration patterns. All external references are to established regulatory frameworks or internal skill components.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided information about medical devices to generate risk documentation. It manages this risk surface by requiring specific clarifications and following a structured ISO-standard workflow, which serves as a functional boundary against potentially malicious instructions embedded in input data.
Audit Metadata