brainstorming-workflows
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured task-based workflow (Task 1 through Task 7) to guide the agent's interaction with the user.
- [COMMAND_EXECUTION]: The skill uses platform-specific task management commands (TaskCreate, TaskUpdate, TaskList) to track progress. These are internal tool calls for state management.
- [DATA_EXPOSURE]: The skill reads a local analysis report (if provided) and writes a summary file to the .rcc/ directory. These operations are limited to the local filesystem and serve the skill's primary purpose of workflow documentation.
- [PROMPT_INJECTION]: The skill includes instructions to prevent the agent from skipping steps or rationalizing shortcuts ("Red Flags
- STOP"), which are safety and compliance mechanisms for ensuring thoroughness rather than malicious overrides.
- [SAFE]: No external network operations, obfuscated code, or credential harvesting patterns were detected in the skill instructions or reference files.
Audit Metadata