The Agent Skills Directory

[SAFE]: The skill functions as a high-level coordinator for customer success workflows, dispatching user input via {{args}} to appropriate sub-skills such as keep-recon and keep-health. This routing behavior is standard and does not include any direct execution of dangerous commands within the router itself.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The instructions are clear and aligned with the stated purpose of the skill.
[SAFE]: The tool access defined in the frontmatter (allowed-tools) is used to restrict the environment, and no actual tool invocation patterns in the text show signs of abuse or privilege escalation.

keep