brutal-honesty-advisor

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFE
Full Analysis
  • [NO_CODE]: The skill is composed exclusively of natural language instructions and examples within a markdown file. It does not contain any executable scripts, binary files, or installation commands.- [PROMPT_INJECTION]: The instructions establish a professional persona for critique and feedback. There are no attempts to override system safety filters, ignore prior instructions, or perform unauthorized role-playing injections.- [DATA_EXFILTRATION]: The skill does not contain any network-related commands or file system access patterns that could lead to data exposure or exfiltration.- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or administrative operations are requested or defined in the skill content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 12:28 PM