The Agent Skills Directory

[SAFE]: The skill is a purely instructional prompt designed to organize and summarize chat history. It does not include executable scripts, external dependencies, or network-enabled tools.
[DATA_EXFILTRATION]: The skill contains specific instructions to redact sensitive information, including API keys, passwords, and personally identifiable information, before generating the output text.
[COMMAND_EXECUTION]: The instructions explicitly prohibit the agent from creating, editing, deleting, or staging files, which mitigates risks associated with unauthorized file system access.
[PROMPT_INJECTION]: No evidence of malicious override patterns, jailbreak attempts, or safety filter bypasses was found in the skill metadata or body.

decision-handoff