← Back to Skills Marketplace
564
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install skill-sec
Description
Security agent that inventories installed OpenClaw skills, analyzes them for threats, and syncs results to your Clawned dashboard.
Usage Guidance
This skill appears to do what it says: it inventories installed skills and (when you explicitly run a scan) uploads selected source/config files to a Clawned server. Before installing or enabling it, consider:
- Only provide CLAWNED_API_KEY if you trust the Clawned service and its privacy/security practices (default server is api.clawned.io). Review their privacy/retention policies.
- 'sync' uploads only metadata (owner, slug, displayName, commit/version). 'scan --path' will upload file contents (up to 30 files, 512KB each) — do NOT run scan on arbitrary or sensitive directories (e.g., repos containing secrets).
- The agent reads ~/.openclaw/openclaw.json to find extra skill directories; make sure that file does not expose unintended paths you don't want scanned.
- The script stores a local state file at ~/.openclaw/clawned_agent.json (agent id, timestamps).
- If you want extra caution: run a quick code review of scripts/agent.py locally, or run the agent in a constrained environment (container) or against a test CLAWNED_SERVER endpoint before using it on production data. If you have low tolerance for uploading any project files, avoid using 'scan --path' or run scans only on copies you control.
Capability Analysis
Type: OpenClaw Skill
Name: skill-sec
Version: 1.0.1
The skill is classified as suspicious due to its high-risk capabilities, despite being explicitly declared in the documentation. The `scripts/agent.py` file, when executing the `scan --path` command, reads the full content of other skill's source files and sends them to the external server `https://api.clawned.io`. While this is declared in `SKILL.md` as part of a security analysis feature, sending arbitrary source code to an external endpoint is a significant trust requirement and a potential data exfiltration risk if the server or skill were compromised. Additionally, the skill accesses `~/.openclaw/openclaw.json` (a `CRED-001` pattern) in `scripts/agent.py` to discover skill directories, even though it claims to only read `extraDirs` and not credentials, this still represents a sensitive file access capability.
Capability Assessment
Purpose & Capability
Name/description, required binary (python3), and required env var (CLAWNED_API_KEY) align with behavior in the code: the agent discovers installed skills and POSTs metadata or, on explicit scan, file contents to a Clawned server. Reading ~/.openclaw/openclaw.json to locate extraDirs is consistent with discovery functionality.
Instruction Scope
SKILL.md and the script keep scope consistent: 'sync' only sends metadata (owner, slug, displayName, latest.commit/version), while 'scan --path' explicitly reads up to 30 scannable files (many config/source extensions) and uploads their contents. The skill explicitly excludes .env files, but other config files (JSON/YAML/TOML, etc.) are collected on explicit scans — users should avoid scanning arbitrary/non-skill directories.
Install Mechanism
No install spec is provided (instruction-only + included Python script). Nothing is downloaded or installed at runtime; risk from install mechanism is low.
Credentials
Only CLAWNED_API_KEY is required (CLAWNED_SERVER is optional). That single credential is proportional to a service that must authenticate to a remote dashboard. The agent does read openclaw.json to find extraDirs, but it does not send that config to the server in normal operation.
Persistence & Privilege
The skill is not auto-included (always:false). It writes a small state file (~/.openclaw/clawned_agent.json) to store agent_id and last sync timestamps — this is reasonable for an agent. There is no evidence it modifies other skills or system-wide config.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install skill-sec - After installation, invoke the skill by name or use
/skill-sec - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Added a new "Data & Privacy" section explaining what metadata and files are collected or sent during `sync` and `scan` commands.
- Clarified that no file contents, secrets, or `.env` files are sent or read during default sync operations.
- Detailed file handling, scan exclusions, and local config access for increased transparency.
v1.0.0
Initial release of the security agent for OpenClaw.
- Inventories all installed OpenClaw skills automatically.
- Analyzes skills for security threats using detection patterns and threat models.
- Syncs security results to the dashboard.
- Includes CLI script (`agent.py`) for manual scan, sync, inventory, and status.
- Provides setup instructions and supports scheduled automatic scans.
Metadata
Frequently Asked Questions
What is skill sec?
Security agent that inventories installed OpenClaw skills, analyzes them for threats, and syncs results to your Clawned dashboard. It is an AI Agent Skill for Claude Code / OpenClaw, with 564 downloads so far.
How do I install skill sec?
Run "/install skill-sec" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is skill sec free?
Yes, skill sec is completely free (open-source). You can download, install and use it at no cost.
Which platforms does skill sec support?
skill sec is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created skill sec?
It is built and maintained by uttamnest (@uttamnest); the current version is v1.0.1.
More Skills