workflow-idea-to-pbi
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses authoritative language such as 'IMPORTANT' and 'MUST' to ensure the agent follows a specific sequence of steps. This is natural instructional language intended to guide a business process and does not attempt to override safety filters or bypass core agent instructions.
- [DATA_EXFILTRATION]: No sensitive file access, hardcoded credentials, or unauthorized network operations were identified.
- [REMOTE_CODE_EXECUTION]: No external script downloads or package installations were found.
- [COMMAND_EXECUTION]: The skill references internal workflow commands (slash commands like
/workflow-start,/idea,/refine). These are used for process navigation within the agent's environment and do not involve arbitrary shell or system command execution.
Audit Metadata