Brutal honest advisor
PassAudited by VirusTotal on May 11, 2026.
Overview
Type: OpenClaw Skill Name: brutal-honesty-advisor Version: 1.0.0 The OpenClaw skill bundle defines an AI agent persona for providing 'brutally honest' feedback. The SKILL.md file contains instructions solely focused on guiding the AI's conversational style, tone, and response structure. There are no instructions for the agent to perform any system operations, access sensitive data, make network requests, execute code, or engage in any activity beyond generating text-based responses. No indicators of prompt injection for malicious purposes, data exfiltration, or system compromise were found.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The assistant may switch to blunt feedback even when the user did not directly ask for it.
This broadens activation beyond explicit user requests and may redirect the conversation into critique mode based on the assistant's inference.
Also trigger when someone shares a plan or idea and appears to be seeking validation rather than genuine critique.
Use this skill when you intentionally want critical feedback, and override it if you want support, brainstorming, or a gentler tone.
Blunt, confident advice may feel authoritative even when it is based on limited context or inference.
The skill instructs the assistant to present strong subjective judgments and inferred motivations as direct truth; this is disclosed and purpose-aligned, but users should not treat every assertion as fact.
Tell the truth, always. ... What you're avoiding or lying to yourself about ... Read between the lines.
Ask for evidence, uncertainty, and alternatives when the feedback could affect important personal, business, or career decisions.