The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for the agent to follow when formatting text. There are no scripts, binaries, or executable commands included in the package.
[SAFE]: The skill configuration in the YAML frontmatter includes disable-model-invocation: true, which is a security-positive setting that prevents the agent from invoking additional tools or models during the execution of this skill, thereby minimizing the attack surface.
[SAFE]: No network operations, credential requirements, or file system interactions were detected. The skill operates solely as a documentation and style guide for security advisory writing.

draft-security-advisory