The Agent Skills Directory

[Prompt Injection] (SAFE): The content consists of instructional text and examples. No attempts to override system prompts, bypass safety filters, or use 'DAN'-style jailbreaks were detected.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths (like SSH or AWS keys), or unauthorized network operations were found. It mentions the standard agent skill path ~/.claude/skills/, which is benign.
[Remote Code Execution] (SAFE): No remote script downloads (e.g., curl | bash) or unverifiable package installations are present. Examples of local script usage are provided for illustrative purposes only.
[Obfuscation] (SAFE): The file contains clear, readable Markdown. No Base64, zero-width characters, or homoglyphs were detected.
[Indirect Prompt Injection] (LOW): While this skill guides the creation of other skills based on user input, it does not ingest untrusted external data at runtime. It functions as a static template for generating structured local files.
[Persistence & Privilege Escalation] (SAFE): No commands were found that attempt to gain root access or establish persistence via shell profiles or system services.

create-skill