← Back to Skills Marketplace
Skillguard
by
Jonathanliu811026
· GitHub ↗
· v1.1.0
· MIT-0
892
Downloads
0
Stars
1
Active Installs
4
Versions
Install in OpenClaw
/install skillguard-audit
Description
Audit OpenClaw skills for security risks before installation via SkillGuard API.
Usage Guidance
This tool does what it says: it fetches skill source (or reads a local file) and sends the full contents to https://api.agentsouls.io for analysis. Before using it, consider: (1) Do you trust the SkillGuard operator? The audit will transmit full source code (including any accidentally committed secrets) to that external service. The SKILL.md claims the code is analyzed in memory and not stored — you must trust that claim. (2) Inspect audit.sh and safe-install.sh yourself (they are included and readable) so you know exactly what will be sent and when clawhub is invoked. (3) Use the provided self‑hosting option or manual review if you cannot expose code externally. (4) Be cautious with the --force flag in safe-install.sh (it bypasses the audit). If these privacy/trust tradeoffs are acceptable, the skill is coherent and appropriate for the stated purpose.
Capability Analysis
Type: OpenClaw Skill
Name: skillguard-audit
Version: 1.1.0
The skill's primary function is to send the full source code of other OpenClaw skills to a remote third-party API (api.agentsouls.io) for analysis. While this behavior is explicitly disclosed in the SKILL.md privacy notice, the automated exfiltration of local or downloaded script content via audit.sh and safe-install.sh poses a significant security risk, as it could lead to the exposure of sensitive logic or hardcoded credentials contained within the audited files to an external service.
Capability Assessment
Purpose & Capability
Name/description match the behavior: the scripts fetch skill files via clawhub, aggregate source, and POST them to https://api.agentsouls.io for analysis. Required binaries (curl, jq, clawhub) are appropriate and proportionate to that purpose.
Instruction Scope
The runtime behavior intentionally reads full skill source (SKILL.md and files with .sh/.js/.ts/.py/.md) and transmits it to the external audit API. This is coherent with an audit tool, but it means the skill will send full source code (including any secrets inadvertently committed) off‑host. The SKILL.md explicitly discloses this, which mitigates surprise but does not eliminate privacy risk.
Install Mechanism
No remote install/downloads or archives; this is an instruction+script bundle. The scripts are plain shell (audit.sh, safe-install.sh) and do not fetch or execute arbitrary remote code themselves. Risk from installation is low because there is no extract/download install mechanism in the skill metadata.
Credentials
No environment variables or credentials are required by the skill. However, the audit relies on a third‑party endpoint (api.agentsouls.io) to receive full source code; that external trust relationship is the primary sensitive requirement. The scripts do not request unrelated credentials, but they will transmit whatever code you give them to the external API.
Persistence & Privilege
The skill does not request permanent inclusion (always:false). It does not modify other skills or system configuration. The wrapper execs clawhub install to perform installations — expected behavior for a pre‑install audit wrapper.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install skillguard-audit - After installation, invoke the skill by name or use
/skillguard-audit - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
Fix: added clawhub to required bins, added Privacy Notice for data transmission disclosure
v1.0.0
Initial release: audit OpenClaw skills for security risks via SkillGuard API (https://api.agentsouls.io)
v0.3.0
Auto-audit on install, audit.sh helper script, certification badges
v0.2.0
Initial release: x402 paid audit, EIP-712 credit/IOU system, 7 threat categories, reputation tracking
Metadata
Frequently Asked Questions
What is Skillguard?
Audit OpenClaw skills for security risks before installation via SkillGuard API. It is an AI Agent Skill for Claude Code / OpenClaw, with 892 downloads so far.
How do I install Skillguard?
Run "/install skillguard-audit" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Skillguard free?
Yes, Skillguard is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Skillguard support?
Skillguard is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Skillguard?
It is built and maintained by Jonathanliu811026 (@jonathanliu811026); the current version is v1.1.0.
More Skills