Automation & Ops drift-detectionfile-integritybaseline-monitoringfile-restorationaudit-logrelease-verificationopenclaw

Soul Guardian File Integrity Guard

Detect and handle unauthorized changes to an agent’s core workspace files.

FollowSkills review · FSRS-2.0
Not recommended
55/ 100 5-point scale 2.8 / 5
Trust17 / 25 · 3.4/5

The code and documentation show no network by default, local-workspace operation, symlink refusal, atomic writes, quarantine copies, hash-chained audit logs, and a signed-release verification procedure. However, restore mode overwrites SOUL.md/AGENTS.md by default without per-event confirmation, state may contain sensitive snapshots and may default inside the workspace, external isolation is not enforced, and the signing-key provenance is not independently confirmed in the supplied material; 8 points are deducted.

Reliability8 / 20 · 2.0/5

The main script, state migration helper, launchd installer, and committed integration tests cover initialization, drift, restore, approval, and audit-chain scenarios, and the static logic is broadly consistent. This review did not execute anything, while permission failures, missing files, concurrent changes, platform differences, and long-running watch behavior have limited coverage and diagnostics; the static cap also limits the score to 10, so 12 points are deducted.

Adaptability10 / 15 · 3.3/5

The audience, OpenClaw workspace use case, commands, default protected files, restore/alert/ignore boundaries, and trigger terms are fairly clear. However, it is primarily OpenClaw-oriented, lacks Chinese-language documentation, and installation or scheduling may depend on npx/GitHub or OpenClaw/macOS; environment-fit evidence is limited, so 5 points are deducted.

Convention10 / 15 · 3.3/5

The skill includes version 0.0.9, AGPL-3.0-or-later licensing, an SBOM, installation and operational notes, limitations, troubleshooting, examples, and a changelog. Information architecture is usable, but maintenance ownership, a clear update path, and publisher responsibility remain insufficiently established, while several installation and state-directory assumptions require user verification; 5 points are deducted.

Effectiveness6 / 15 · 2.0/5

The core task is to detect workspace-file drift, produce diffs, record audit events, and restore critical files. The documentation provides directly usable commands and examples, and committed tests cover the main workflow. Static review did not execute it, independent verification of restoration and alert delivery is absent, and users still must initialize baselines, configure scheduling, and secure state storage; 9 points are deducted.

Verifiability4 / 10 · 2.0/5

The submission provides full source, a pinned version, signed-release verification instructions, an SBOM, and committed tests, enabling meaningful audit and review. There are no execution results or independent third-party reproductions in the supplied material, and the signing artifacts and key release claims are not cross-validated here; 6 points are deducted.

Evidence confidence:Low Reviewed Jul 20, 2026 Reviewed revision eac8392f8ac9
Before you use it
  • Restore mode automatically overwrites protected files; confirm the baseline, policy, and recovery scope before enabling it, and keep separate backups.
  • The state directory contains approved snapshots, diffs, and quarantined files that may expose prompts, identity data, or memory; place it outside the workspace with restrictive permissions.
  • Core operation is local by default, but installation verification, npx installation, and retrieval of remote release artifacts may depend on GitHub or other overseas network reachability.
  • This assessment is based only on static source review; scripts, tests, and signature verification were not executed.
See the full review method →

What does this skill do, and when should you use it?

Soul Guardian is the ClawSec skill for protecting OpenClaw workspace files such as SOUL.md and AGENTS.md. It compares files with approved SHA-256 baselines, can restore selected files automatically, creates unified diffs, and emits security alerts. It also provides continuous monitoring, intentional-change approval, and hash-chained audit-log verification. Adopt it when protecting agent identity and instruction files matters, but account for the fact that restore mode intentionally overwrites drifted files.

Uses python3 to read protected workspace files and compare them with approved SHA-256 baselines; detects drift and, under the default policy, restores SOUL.md and AGENTS.md while alerting on USER.md, TOOLS.md, IDENTITY.md, HEARTBEAT.md, and MEMORY.md and ignoring memory/*.md; writes local audit and quarantine state and saves unified diffs; provides check, watch, approve, status, and verify-audit commands for detection, continuous monitoring, approval, status inspection, and audit verification; supports --output-format alert for human-readable alerts suitable for forwarding to a user.

  1. An OpenClaw administrator wants heartbeat checks to detect unexpected changes to SOUL.md or AGENTS.md.
  2. A personal agent owner needs automatic restoration of approved identity and behavior instructions after file drift.
  3. A workspace maintainer wants alerts for USER.md, TOOLS.md, or MEMORY.md without automatic overwrites.
  4. A security maintainer needs diffs and hash-chained audit records to investigate recurring file changes.
  5. A standalone-package user wants to verify the signed release manifest before trusting SKILL.md, skill.json, or the archive.

What are this skill's strengths and limitations?

Pros
  • Provides SHA-256 baseline drift detection and unified diff output.
  • Can restore and alert on changes to SOUL.md and AGENTS.md.
  • Uses hash-chained audit logging, atomic restore writes, and refuses to operate on symlinks.
  • Has no network behavior by default, and scheduling is opt-in.
Limitations
  • Restore mode overwrites drifted files, so false positives can replace intentional edits.
  • It cannot prove who made a change; actor information is best-effort metadata.
  • It cannot protect against an attacker controlling both the workspace and state directory.
  • It is not a backup replacement, and the source provides no test-suite or cross-platform execution evidence.

How do you install this skill?

Install with the Vercel Skills CLI:

npx skills add prompt-security/clawsec --skill soul-guardian -a openclaw -y

For standalone installation, follow the supplied verification procedure to validate the signed release manifest, archive, SKILL.md, and skill.json before installing or extracting the archive. The source does not document installation directories or commands for other platforms.

How do you use this skill?

Initialize baselines in the OpenClaw workspace:

cd ~/.openclaw/workspace
python3 skills/soul-guardian/scripts/soul_guardian.py init --actor setup --note "initial baseline"

Enable monitoring guidance:

python3 skills/soul-guardian/scripts/soul_guardian.py enable-monitoring

For heartbeat-based checks, add this to HEARTBEAT.md:

## Soul Guardian Check
- Run python3 skills/soul-guardian/scripts/soul_guardian.py check --actor heartbeat --output-format alert
- If any output is produced, relay it to the user immediately as a security alert

You can also run watch --interval 30 for continuous checks, approve --file <path> for reviewed intentional changes, status for current state, and verify-audit for audit-log validation.

How does this skill compare with similar options?

The README distinguishes soul-guardian from the repository’s other security skills: it focuses on OpenClaw file drift detection and baseline restoration, rather than advisory feeds, vulnerability scanning, supply-chain installation verification, or runtime traffic monitoring.

FAQ

Does it modify files automatically?
Yes. By default, drift in SOUL.md and AGENTS.md triggers automatic restoration and an alert. Files using alert mode only produce alerts.
Does it require network access?
Normal operation has no network behavior by default. Standalone release verification uses curl to download artifacts from GitHub Releases.
How do I approve an intentional change?
Review the saved diff first, then run python3 skills/soul-guardian/scripts/soul_guardian.py approve --file <path> --actor user --note "intentional update".
Can it protect against an attacker who changes all state?
No. If the attacker controls both the workspace and state directory, the skill cannot protect the baseline. The documentation recommends storing state outside the workspace.

More skills from this repository

All from prompt-security/clawsec

Automation & Ops

OpenClaw Traffic Guardian

A scoped, opt-in runtime traffic monitoring baseline for OpenClaw.

Automation & Ops

OpenClaw Audit Watchdog

Automates daily OpenClaw security audits and delivers actionable reports.

Automation & Ops

Hermes Attestation Guardian

Generate verifiable Hermes security attestations and detect authenticated baseline drift.

Automation & Ops

NanoClaw Traffic Guardian

A host-managed baseline for optional NanoClaw traffic inspection and runtime security findings.

Automation & Ops

ClawSec Advisory Feed

Keep OpenClaw agents informed about emerging security threats.

Automation & Ops

ClawSec Suite Manager

Protect OpenClaw skill installs with signed advisories, risk checks, and approval-gated responses.

Automation & Ops

Hermes Traffic Guardian

A consent-based, auditable baseline for monitoring Hermes runtime traffic.

Automation & Ops

Picoclaw Traffic Guardian

An opt-in, detect-and-log baseline for monitoring Picoclaw gateway traffic and exporting security posture data.

Automation & Ops

ClawHub Reputation Gate

Checks ClawHub reputation before OpenClaw skill installation and requires explicit approval for low-scoring skills.

Automation & Ops

ClawSec Scanner

Unify dependency, CVE, source-code, and OpenClaw hook risk scanning in one agent-security workflow.

Automation & Ops

Picoclaw Security Guardian

A read-first security layer for Picoclaw advisory checks, configuration drift detection, and signed release verification.

Automation & Ops

Picoclaw Security Posture Review

Review Picoclaw security posture in read-only mode and give operators safe remediation guidance.

Automation & Ops

ClawSec Release Manager

A maintainer workflow for versioning, releasing, and verifying Claw skills through GitHub.

Automation & Ops

NanoClaw Security Sentinel

Check NanoClaw skills for known risks before installation and during operation.

Automation & Ops

Clawtributor Security Reporter

Prepare sanitized AI-agent incident reports for explicit human approval before submission.

Related skills