Munger Decision
PassAudited by ClawScan on May 10, 2026.
Overview
The provided artifacts describe a local decision-analysis assistant with no evidence of credential use, network access, destructive actions, or hidden behavior.
This appears safe to use as a local decision-structuring assistant. Be mindful that your prompts and answers may include sensitive investment, hiring, or business information, and treat its output as decision support rather than professional financial or legal advice. Do not run the optional npm development commands unless you intend to inspect or develop the package.
Findings (2)
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.
Your decision details and answers may be retained within the assistant's session or history flow while it prepares a report.
The skill documents collecting user answers during a decision session and provides a history command. This is expected for a guided decision assistant, but users may enter sensitive financial, personnel, or business information.
"查看历史记录" / "收集用户回答" / "answers: Record<string, string[]>"
Avoid entering highly confidential details unless you are comfortable with the assistant using them for the session/report, and clear any history if the platform provides that option.
If you choose to run the developer setup commands, npm dependencies may be installed and package scripts may run according to the package configuration.
The development guide includes manual npm-based setup commands. This is not an automatic install mechanism, but running npm install executes dependency installation for the included package.
cd /root/.openclaw/workspace/agents/main/skills/munger-decision npm install
Only run the development commands if you intend to inspect or modify the skill, and review package.json/package-lock.json first.