← Back to Skills Marketplace
1551
Downloads
1
Stars
3
Active Installs
3
Versions
Install in OpenClaw
/install openclaw-sentinel
Description
Supply chain security for agent skills. Pre-install inspection, post-install scanning, obfuscation detection, and known-bad signature matching. Verify skills are safe before they touch your workspace. Free alert layer — upgrade to openclaw-sentinel-pro for quarantine, blocking, and community threat feeds.
Usage Guidance
This appears to be a legitimate local supply-chain scanner that only needs python3 and will read and write under your OpenClaw workspace. Before installing or running: (1) obtain the repository from a trusted source (registry shows no homepage), (2) review the full scripts/sentinel.py for any code paths that rename/move skill directories or make outbound network calls, (3) run it first in a copied/isolated workspace if you are worried about quarantine actions, (4) confirm whether importing community threat lists (--update-from) is local-only or can fetch remote feeds, and (5) note the metadata mismatch: OPENCLAW_WORKSPACE is used but not declared as a required env var in the registry. If you need higher assurance, request the maintainer's source URL and verify release signatures before trusting automated quarantining or updates.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-sentinel
Version: 1.0.2
The OpenClaw Sentinel skill is a security scanner designed to detect supply chain risks in other skills. Its Python script (`scripts/sentinel.py`) strictly adheres to its stated purpose and claims of 'No External Dependencies' and 'No network calls', using only standard library modules and performing local file system operations. The patterns and behaviors it identifies (e.g., `eval(base64.b64decode(...))`, `os.system()`, `socket.connect()`) are for *detection* in other skills, not for self-execution. Features like 'quarantine' and 'reject' involve renaming or moving skill directories within the workspace, which are legitimate defensive actions. There is no evidence of intentional harmful behavior, data exfiltration, backdoors, or prompt injection attempts in `SKILL.md` or `README.md`.
Capability Assessment
Purpose & Capability
Name and description match what is present: a Python-based scanner that inspects skill directories for obfuscation, suspicious patterns, and known-bad hashes. Required binary is only python3, which is appropriate for the functionality.
Instruction Scope
Runtime instructions tell the agent to scan or inspect skill directories and to read/write local workspace state (e.g., create .sentinel, .quarantine). That behavior is within scope for a scanner, but the skill will traverse and read many files under your workspace and will persist scan results and a threat DB under workspace/.sentinel (and may write quarantine evidence to workspace/.quarantine). The SKILL.md documents these behaviors; however, confirm whether any quarantine or write actions are optional or require explicit consent before enabling.
Install Mechanism
No install spec (instruction-only with included script). Nothing pulls remote code at runtime; the code claims to use only the Python standard library and does not declare external package installs. This is low installation risk, but you should obtain the skill from a trusted source (the registry metadata lists no homepage).
Credentials
The skill does not request credentials and only needs python3. It uses OPENCLAW_WORKSPACE (and falls back to current directory / ~/.openclaw/workspace) to locate the workspace — that environment variable is referenced in SKILL.md but is not listed in the registry 'required env vars' field, which is a metadata mismatch. The scanner also looks for code that reads env vars inside scanned skills (e.g., patterns for SECRET/TOKEN usage) — that is expected for a scanner but means the tool will surface secrets usage patterns if present in scanned files (it does not itself require secrets).
Persistence & Privilege
always:false and model invocation allowed (default). The tool writes its own data under the target workspace (.sentinel, .quarantine) which is expected for a scanner. There is code and constants related to quarantining, but SKILL.md/README state that automated blocking/quarantine features are part of a 'pro' offering — verify whether any destructive actions (renaming/moving skill dirs) are opt-in.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-sentinel - After installation, invoke the skill by name or use
/openclaw-sentinel - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
openclaw-sentinel 1.0.2
- Removed mention of "openclaw-sentinel-pro" and premium features from documentation.
- Cleaned and simplified documentation to focus only on free and core supply chain security scanner capabilities.
- No changes to functionality or core commands; documentation only.
v1.0.1
**Major update: Shifts focus from workspace file integrity to supply chain security for agent skills.**
- Adds deep scanning for skill supply chain threats: obfuscated code, dynamic imports, known-bad hashes, install-time risk behaviors, and more.
- New Python script (`scripts/sentinel.py`) replaces previous integrity script.
- Removes file integrity baseline/verification logic and related commands.
- Updates all documentation to reflect the new scanning and threat detection features, including risk scoring and threat database management.
- Skill description and emoji updated to emphasize pre-install inspection and supply chain security.
v1.0.0
OpenClaw Sentinel 1.0.0 initial release:
- Monitors core agent files (SOUL.md, AGENTS.md, IDENTITY.md, memory files, skill manifests, and configs) for unauthorized modifications.
- Scans for prompt injection patterns, including hidden instructions, base64 payloads, Unicode tricks, markdown exfiltration, and system prompt markers.
- Provides baseline establishment, integrity verification, injection scanning, acceptance workflows, and one-line status checks.
- Designed for cross-platform use (Mac, Linux, Windows) with no external dependencies.
- Serves as a free detection layer; automated response available via upgrade.
Metadata
Frequently Asked Questions
What is Openclaw Sentinel?
Supply chain security for agent skills. Pre-install inspection, post-install scanning, obfuscation detection, and known-bad signature matching. Verify skills are safe before they touch your workspace. Free alert layer — upgrade to openclaw-sentinel-pro for quarantine, blocking, and community threat feeds. It is an AI Agent Skill for Claude Code / OpenClaw, with 1551 downloads so far.
How do I install Openclaw Sentinel?
Run "/install openclaw-sentinel" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Openclaw Sentinel free?
Yes, Openclaw Sentinel is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Openclaw Sentinel support?
Openclaw Sentinel is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux, win32).
Who created Openclaw Sentinel?
It is built and maintained by AtlasPA (@atlaspa); the current version is v1.0.2.
More Skills