The Agent Skills Directory

[Prompt Injection] (SAFE): No malicious override patterns or jailbreak instructions detected. The instructions are focused on documentation standards and stylistic constraints.
[Data Exposure & Exfiltration] (SAFE): No evidence of sensitive file access, credential usage, or network requests to external domains.
[Remote Code Execution] (SAFE): No remote scripts, package installations, or piped command executions are present.
[Indirect Prompt Injection] (LOW): The skill ingests untrusted data through the $ARGUMENTS variable. While it lacks explicit boundary markers or sanitization, the skill possesses no dangerous capabilities (such as file-writing or network access) that could be exploited via malicious input. The risk is limited to stylistic subversion of the generated documentation.

documentation