planning

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a structured workflow for project planning and dependency management without any malicious intent or suspicious commands.
  • [DATA_EXFILTRATION]: Network activity and access to sensitive system files are absent. The skill only utilizes the 'Write' tool to manage a local planning file (./.prd) within the current working directory.
  • [COMMAND_EXECUTION]: While the skill orchestrates work through subagents, it does not invoke arbitrary shell commands, system calls, or third-party executables.
  • [PROMPT_INJECTION]: The use of 'CRITICAL' and 'IMPORTANT' markers is restricted to structural workflow enforcement and does not attempt to bypass agent safety guidelines or override core system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 11:15 AM