qe-brutal-honesty-review
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown-based instructions and templates. No scripts, binaries, or configuration files are included in the package.
- [PROMPT_INJECTION]: The skill defines a specific persona (Linus/Ramsay/Bach) for technical criticism. While it uses strong language ('brutal', 'harsh'), it includes explicit safety guidelines and ethical constraints, such as 'Attack the work, not the worker' and lists of contexts where the skill should not be applied (e.g., junior developers or low-safety environments). It does not attempt to override system prompts or bypass safety filters.
- [EXTERNAL_DOWNLOADS]: No remote resources, package registries (npm/pip), or external script execution patterns were detected.
- [DATA_EXFILTRATION]: The skill contains no network-capable code or instructions to access sensitive file paths like credentials or configuration files.
Audit Metadata