The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based technical writing guidelines without any executable scripts, tool calls, or configuration files that would introduce security vulnerabilities.
[PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety guidelines was found. The guidance regarding the yomiyasu skill is a functional workflow constraint rather than an attempt to override system rules.
[DATA_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or network operations were detected in the skill instructions.
[OBFUSCATION]: The Japanese text used throughout the document consists of legitimate linguistic examples and formatting rules. There are no signs of homoglyph attacks, zero-width characters, or hidden payloads.
[INDIRECT_PROMPT_INJECTION]: While the skill directs the agent on how to handle user-provided prose, it does not ingest untrusted external data (such as web content) and lacks the capabilities (like file writes or network access) that would make it a significant target for indirect injection attacks.
[REMOTE_CODE_EXECUTION]: There are no patterns of remote code execution, package installations, or dynamic code generation.

technical-writing