The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown-formatted instructions, style guides, and templates. No scripts, binaries, or executable code of any kind are included in the package.
[SAFE]: No network operations, external data fetching, or exfiltration patterns were detected. All references are to internal files provided with the skill or user-supplied text during the generation process.
[SAFE]: The skill does not attempt to access sensitive system files, environment variables, or credentials. It only references a non-sensitive configuration file (brand/VOICE.md) to define writing tone.
[SAFE]: No prompt injection, jailbreak attempts, or behavior overrides were found in the instructions or templates.
[SAFE]: While the skill processes user-supplied data (blog topics and key points), it lacks any tools or capabilities (such as file-writing, command execution, or network calls) that could be exploited via indirect prompt injection.

content-blog