OpenClaw Warden Pro

ReviewAudited by ClawScan on May 10, 2026.

Overview

This appears to be a coherent local workspace security tool, but its recommended automatic protection mode can overwrite important workspace files and disable skills without per-action confirmation.

Install only if you want a local tool that can actively change your agent workspace. Before enabling the recommended automatic `protect` hook, create a baseline intentionally, test scan results manually, and make sure you know how to restore or unquarantine legitimate files and skills.

Findings (4)

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

A mistaken detection could restore over legitimate edits, roll back important workspace files, or disable a skill by quarantining it.

Why it was flagged

The default recommended protection workflow can automatically modify workspace state and disable skills. That is purpose-aligned for a security tool, but it is high-impact and the artifacts do not describe a confirmation gate, dry run, or false-positive handling before automatic changes.

Skill content
`protect` | Full scan + auto-restore + auto-quarantine + flag
Recommendation

Run `verify`, `scan`, or `full` manually first, establish and review the baseline, and only enable `protect` automation after confirming the rules work for your workspace.

NoteHigh Confidence
ASI10: Rogue Agents
What this means

Once configured, the tool may repeatedly run and change the workspace at session start or during periodic checks.

Why it was flagged

The artifact recommends recurring automatic execution through startup and heartbeat integrations. This is disclosed and user-configured, but it means the skill can keep taking protection actions after initial setup.

Skill content
Session Startup Hook ... "command": "python3 scripts/integrity.py protect" ... Add to HEARTBEAT.md for periodic protection
Recommendation

Only add the startup hook or heartbeat entry if you want ongoing automatic enforcement; otherwise invoke scans manually.

What this means

Old copies of sensitive workspace files may remain under the integrity snapshot directory even after the originals change.

Why it was flagged

The skill creates persistent local snapshots used for restore. These files may include instructions, configuration, or other private workspace content.

Skill content
Critical, config, and skill files are automatically snapshotted when the baseline is established.
Recommendation

Treat the `.integrity` snapshot area as sensitive, avoid storing secrets in monitored files, and remove snapshots if uninstalling or resetting the tool.

What this means

It is harder to verify provenance or updates for a tool that can automatically change your workspace.

Why it was flagged

The registry metadata does not provide a verified source or homepage, while the tool has authority to modify important workspace files and skill directories.

Skill content
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
Recommendation

Review the included script from the package you install, compare it against a trusted upstream if available, and pin or archive the reviewed version.