The Agent Skills Directory

[PROMPT_INJECTION]: No attempts to override system instructions, bypass safety filters, or extract system prompts were detected. The instructions focus purely on the intended task of structured reflection.
[DATA_EXFILTRATION]: The skill does not contain any network-related commands (curl, wget, etc.) or access to sensitive file paths like credentials or SSH keys.
[REMOTE_CODE_EXECUTION]: No remote scripts are downloaded or executed. All logic is contained within the markdown instructions.
[COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or privilege escalation attempts (sudo, chmod).
[CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or secrets were found in the skill content.
[SAFE]: All references to external skills (e.g., moai-productivity, moai-wealth) are within the author's own namespace and represent legitimate cross-skill integration for productivity workflows.

retro-builder