Principles
PassAudited by VirusTotal on May 12, 2026.
Overview
Type: OpenClaw Skill Name: principles Version: 1.0.0 The OpenClaw AgentSkills skill bundle is benign. The `SKILL.md` file outlines a personal knowledge management system, instructing the AI agent to create, read, and write files exclusively within a user-specific `personal/` directory. All file system operations are directly aligned with the stated purpose of managing notes, wisdom, and principles. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent's core function or perform unauthorized actions. The instructions are clear, transparent, and limited to local file management within the designated workspace.
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.
Running the reflect workflow may change or remove raw notes from inbox.md after they are processed.
The skill directs the agent to modify local knowledge files and clear the inbox as part of the user-triggered processing workflow.
7. **Clean up** `inbox.md` after processing 8. **Update** `principles/_index.md` if new principles were added
Review important inbox content before processing or keep backups if preserving raw entries matters.
Personal beliefs and reflections may persist across sessions and could influence later reasoning if reused by the agent.
The skill intentionally stores user thoughts, journal entries, wisdom claims, principles, and related context in persistent workspace files.
Everything lives in `personal/` under the user's workspace. Create the directory structure on first use if it doesn't exist.
Avoid storing secrets, periodically review the personal/ files, and treat saved claims as user notes rather than authoritative instructions.