The Agent Skills Directory

[SAFE]: No security vulnerabilities were identified. The skill is explicitly defined as read-only and focuses on parsing local markdown documentation.
[PROMPT_INJECTION]: No instruction override patterns, role-play injections, or system prompt extraction attempts were detected.
[DATA_EXFILTRATION]: No network operations, hardcoded credentials, or sensitive file path access patterns were found. The skill processes project-specific documentation paths.
[COMMAND_EXECUTION]: No shell commands, subprocess invocations, or privilege escalation attempts are present in the skill code or reference files.

arch-flow