Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add edimuj/vexscan --skill openclawgit clone --depth 1 https://github.com/edimuj/vexscanWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/edimuj/vexscan/openclaw)<a href="https://agentmods.dev/skills/edimuj/vexscan/openclaw"><img src="https://agentmods.dev/badge/skills/edimuj/vexscan/openclaw/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/edimuj/vexscan/openclaw"><img src="https://agentmods.dev/badge/skills/edimuj/vexscan/openclaw.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01151 |
| Opus 5.5 | $0.00000 | $0.00460 |
| Sonnet 5.5 | $0.00000 | $0.00230 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
openclaw scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vexscan Security Scanner
Scans extensions, skills, and code for security threats: prompt injection, malicious code, obfuscation, data exfiltration. Also scans inbound messages for injection patterns automatically.
Use it when:
- User wants to install a new extension or skill
- User asks about security of their setup
- User mentions suspicious behavior from an extension
- User wants to audit installed extensions
- User asks about or wants to manage trust decisions
- Before recommending any third-party extension
Action routing
| User intent | Action |
|---|---|
| "Install this extension from GitHub" | install — vets then installs |
| "Is this extension safe?" | vet — scan without installing |
| "Is my setup secure?" | scan — scan all extensions |
| "This extension is acting weird" | scan on that extension's path |
| "Check this text for injection" | check — stdin text scanning (not yet exposed as tool action; use /check slash command) |
| "What's trusted?" / "Show trust entries" | trust_list |
| "Stop trusting X" | trust_revoke |
Install (vet + install in one step)
Always prefer install over vet when the user wants to add an extension.
{ "action": "install", "source": "https://github.com/user/extension" }
Success: { "ok": true, "action": "installed", "findings": 0, "message": "..." }
Blocked: { "ok": false, "action": "install_blocked", "verdict": "high_risk", "findings": 3, "maxSeverity": "high", "reason": "..." }
Severity gates
| Max severity | Default | Override |
|---|---|---|
| Critical | Blocked | Cannot override |
| High | Blocked | "allowHigh": true |
| Medium | Blocked | "force": true |
| Low / Info | Allowed | — |
Never set allowHigh or force without explaining the risks to the user first.
Scan
{ "action": "scan", "path": "~/.openclaw/extensions" }
Path defaults to ~/.openclaw/extensions if omitted. Returns findings count, max severity, and breakdown by severity level.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 124 lines · 0 tokens per session scan A dc480d5072f8
openclaw is a skill published in the GitHub repository edimuj/vexscan (9 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,151 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
specialized-attack-playbooks
A collection of cybersecurity playbooks for investigating and exploiting specific systems, including GoEdge CDN, ARP man-in-the-middle attacks, BT Panel, OCS, MinIO, and CDN-to-S3 access chains.
binary-mobile-reversing
A skill for examining Android packages, Windows executables, native libraries, and some cross-platform app binaries to understand how they work.
youtube-search
Use when the user wants to find YouTube content on any topic: searching for videos or channels, finding creators who cover a subject, discovering tutorials, talks, or expert discussions, or looking up a channel by name or handle. Also use proactively when the user wants to research a topic and YouTube is a good…
pentest-verification
Pravidlá na overovanie bezpečnostných nálezov pomocou konkrétnych dôkazov namiesto domnienok.
kimaki-tunnel
Share a local dev server with the user through a public URL. Use when the user should open a localhost app in a browser, test a webhook or OAuth callback against a local server, or preview a dev server from Discord. Runs kimaki tunnel in a named background tuistory session. ALWAYS load before starting a dev server the…