Claw History

ReviewAudited by ClawScan on May 1, 2026.

Overview

This instruction-only skill is coherent for auditing agent history, but it intentionally reads and encourages retaining memory, session, and command logs that may contain sensitive activity.

This skill appears benign and purpose-aligned for producing an agent accountability timeline. Before installing or running it, be aware that it may surface prior session details and command history, especially if you enable the recommended logging hooks.

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.

What this means

Running the skill may reveal prior conversations, tool use, commands, and operational details from earlier sessions.

Why it was flagged

The skill instructs the agent to read persistent memory, session history, sub-agent history, and tool logs to produce a lifetime timeline. This is aligned with the stated auditing purpose, but it can expose sensitive historical context.

Skill content
Required Data Sources: 1. Earliest and recent `memory/YYYY-MM-DD*.md` files... 3. Available session inventory/history (main + sub-agent sessions when accessible). 4. Current conversation/tool logs.
Recommendation

Use it only when you want a broad accountability report, and consider reviewing or redacting memory/session/command logs if they may contain secrets or private information.

What this means

Enabling the recommended hooks can create longer-lived records of session content and commands on the local system.

Why it was flagged

The README recommends enabling hooks that persist session context and command events. This is disclosed and useful for the skill's timeline purpose, but it increases the amount of historical data retained for later use.

Skill content
`session-memory` (recommended): saves session context on `/new` into `workspace/memory/...`; `command-logger` (strongly recommended): writes command events to `~/.openclaw/logs/commands.log`
Recommendation

Enable these hooks only if you are comfortable retaining this audit data, and check your OpenClaw log retention and access controls.