planning
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behaviors or security risks detected. The skill is functionally focused on project orchestration and planning.
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface (Category 8). While the skill reads task data that could potentially contain instructions, this is inherent to its purpose as a planner. 1. Ingestion points: The agent reads the subject and description fields from the ./.prd JSON file in SKILL.md. 2. Boundary markers: No specific delimiters or 'ignore' instructions are used to wrap the task data. 3. Capability inventory: The skill utilizes the 'Write' tool for file management and refers to a 'Task tool' for spawning subagents. 4. Sanitization: No explicit sanitization or validation of the task content is performed prior to processing.
Audit Metadata