The Agent Skills Directory

[SAFE]: The skill operates by reading local project-specific files within the .gsd/ directory to validate planning metadata. These operations are restricted to project documentation and do not target sensitive system paths or credentials.
[SAFE]: No network operations or data exfiltration patterns were detected. The skill does not utilize network-enabled tools or attempt to send data to external domains.
[SAFE]: The instructions do not involve remote code execution, dynamic package installation, or privilege escalation techniques. It does not use eval, exec, or shell-level command execution.
[SAFE]: No prompt injection or obfuscation was found. The skill's instructions are clear and follow standard role-based task delegation without attempting to bypass safety filters or override system constraints.

plan-checker