The Agent Skills Directory

[SAFE]: The skill is a pure prompt instruction set designed to summarize conversation history and agent actions. It does not perform any file system access, network operations, or external data retrieval.
[SAFE]: No obfuscation, prompt injection attempts, or persistence mechanisms were detected in the instructions or metadata.
[SAFE]: The skill includes 'disable-model-invocation: true' in its frontmatter, which prevents the agent from calling tools while executing this specific summarization task, further reducing the attack surface.
[SAFE]: No credentials, secrets, or sensitive environment variables are requested or hardcoded.
[SAFE]: The strict output constraints (3-5 bullets, 120-character limit) effectively limit the potential for the skill to be used as a vector for secondary prompt injection or data leakage.

cmd-what