Openclaw Default Agent Backstory

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
ASI08: Cascading Failures
What this means

The skill may change how the default agent behaves in later sessions.

Why it was flagged

These are persistent context files that can influence future agent behavior across sessions, so a poor or unintended generated default could carry forward.

Skill content
In `bootstrap` mode, ensure these files exist at workspace root with usable starter content: `AGENTS.md`, `SOUL.md`, `TOOLS.md`, `IDENTITY.md`, `USER.md`, `HEARTBEAT.md`, `BOOTSTRAP.md`.
Recommendation

Review the generated file diffs, especially AGENTS.md, SOUL.md, USER.md, HEARTBEAT.md, and MEMORY.md, before relying on the new agent baseline.

What this means

Personal preferences, routines, decisions, or work details may be stored and reused by the agent later.

Why it was flagged

The skill sets up persistent memory that is reused as future context, which can retain sensitive details or preserve incorrect information if not reviewed.

Skill content
Session start: read `AGENTS.md`, `SOUL.md`, `USER.md`, latest daily memory, and `MEMORY.md` in main/direct chats. During session: write notable decisions and commitments to today's daily file.
Recommendation

Do not place secrets in these memory files, review daily notes periodically, and prune outdated or sensitive entries.