planning-and-task-breakdown
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill's primary function is to guide the agent in generating well-structured, autonomous work orders for development tasks.
- [COMMAND_EXECUTION]: The task template includes a section for verification shell commands (e.g.,
npm test). These commands are placeholders for the agent to use during the implementation phase and are not executed by the skill itself. - [PROMPT_INJECTION]: The skill ingests data from external files like specifications and architecture decision records. While this creates a potential surface for indirect prompt injection if those files contain malicious instructions, the risk is managed by the requirement for independent verification steps and adherence to established project constraints.
Audit Metadata