tldr
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines UI/UX behavior and formatting rules for a persistent 'TL;DR' mode. It does not utilize tools for command execution, network access, or file modification.
- [SAFE]: The skill references a local file
../asd-ste100/SKILL.mdto adopt a specific linguistic style (Simplified Technical English). This is a standard intra-repository reference for configuration and does not constitute a remote code execution risk. - [SAFE]: Instructions regarding the persistence of the mode ('Never self-disable') are related to user experience and conversation state management, not an attempt to bypass agent safety guidelines. The instructions explicitly mention including 'material warnings,' which supports safety transparency.
- [SAFE]: No obfuscation, data exfiltration patterns, or credentials were found in the skill content.
Audit Metadata