ai-tells
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown-based writing guidelines and reference documents. No executable scripts (Python, Node.js, Shell) are present in the package.
- [SAFE]: No sensitive data exposure, hardcoded credentials, or network exfiltration patterns were detected. The only external link provided is a standard GitHub repository reference for documentation purposes in
UPSTREAM.md. - [SAFE]: The instructions in
SKILL.mdare focused on linguistic patterns (avoiding fillers, specific constructions, and clichés). There are no attempts to bypass safety filters or override system-level agent behavior. - [SAFE]: No obfuscation techniques (Base64, homoglyphs, or hidden characters) were found. The content is fully transparent and readable.
- [SAFE]: The skill does not use dynamic context injection or any features that could lead to unauthorized command execution.
Audit Metadata