OpenClaw 16 MBTI

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

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.

NoteHigh Confidence
ASI01: Agent Goal Hijack
What this means

The assistant may give advice through a deliberately selected persona lens, which can make recommendations more forceful, cautious, emotional, or experimental depending on the profile.

Why it was flagged

The skill is designed to change how the assistant frames and prioritizes responses. This is clearly disclosed and central to the purpose, but users should understand that the output is stylized rather than neutral.

Skill content
This skill transforms the AI's communication tone, decision-making focus, and task evaluation criteria by adopting one (or multiple) of the 16 MBTI personality archetypes.
Recommendation

Use the skill when you want a stylized perspective, and ask for a neutral or safety-focused review before acting on important decisions.

What this means

Some persona outputs may sound confident or encourage aggressive tactics, which could be inappropriate for legal, compliance, workplace, or public-facing decisions.

Why it was flagged

One persona profile includes intentionally risk-tolerant, gray-area business framing. It is presented as a stylized persona with a risk warning, not as hidden behavior, but users should not treat it as compliance-safe advice.

Skill content
这个打法确实游走在平台规则的灰色地带。建议提前准备一份致歉声明压在抽屉里,万一被警告,我们秒撤回认错。
Recommendation

Treat persona output as brainstorming or writing style guidance; verify risky business, legal, HR, or compliance actions independently.