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 karimhabush/cyberowl --skill skillgit clone --depth 1 https://github.com/karimhabush/cyberowlWrote 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/karimhabush/cyberowl/skill)<a href="https://agentmods.dev/skills/karimhabush/cyberowl/skill"><img src="https://agentmods.dev/badge/skills/karimhabush/cyberowl/skill/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/karimhabush/cyberowl/skill"><img src="https://agentmods.dev/badge/skills/karimhabush/cyberowl/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00155 | $0.02646 |
| Opus 5 | $0.00077 | $0.01323 |
| Sonnet 5 | $0.00031 | $0.00529 |
| Haiku 4.5 | $0.00015 | $0.00265 |
Grade A, and why
cyberowlai 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 9d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CyberOwl Security Check
Cross-reference recent cybersecurity alerts from 10 international CERTs against the user's project to surface vulnerabilities that actually matter to them.
High-level workflow
- Discover the project's full tech stack (dependencies, infra, frameworks)
- Fetch the alert feed from
https://cyberowlai.com/alerts.json - Match alerts against the stack using tiered confidence
- Report only what's relevant, plus always-flag critical alerts
Run steps 1 and 2 in parallel when possible — don't make the user wait.
Step 1 — Deep project discovery
Build a comprehensive inventory. Go beyond top-level deps — look at transitive dependencies, container base images, CI tool versions, and code import patterns.
1a. Find all dependency and config files
Use Glob to locate files. Search for all of the following (skip categories that return nothing):
| Category | Files to find |
|---|---|
| Node.js | package.json, package-lock.json, yarn.lock, pnpm-lock.yaml |
| Python | requirements.txt, Pipfile, Pipfile.lock, pyproject.toml, poetry.lock, setup.py, setup.cfg |
| Go | go.mod, go.sum |
| Ruby | Gemfile, Gemfile.lock |
| Java/Kotlin | pom.xml, build.gradle, build.gradle.kts |
| Rust | Cargo.toml, Cargo.lock |
| PHP | composer.json, composer.lock |
| C#/.NET | *.csproj, packages.config, Directory.Packages.props |
| Swift | Package.swift |
| Dart/Flutter | pubspec.yaml |
| Elixir | mix.exs |
| Perl | cpanfile |
| Containers | Dockerfile, Containerfile, docker-compose.yml, docker-compose.yaml |
| Kubernetes | *.yaml in k8s/, kubernetes/, deploy/, manifests/ |
| Helm | Chart.yaml, values.yaml |
| Terraform | *.tf |
| Ansible | *.yml in ansible/, playbooks/ |
| Vagrant | Vagrantfile |
| CI/CD | .github/workflows/*.yml, .gitlab-ci.yml, Jenkinsfile, .circleci/config.yml, azure-pipelines.yml |
| Build | Makefile, Taskfile.yml, Justfile |
| Web servers | nginx.conf, nginx/*.conf, apache2.conf, .htaccess, httpd.conf, Caddyfile, traefik.yml, traefik.toml |
| Databases | prisma/schema.prisma, config/database.yml, alembic.ini |
| Env files | .env.example, .env.sample |
| Version files | .node-version, .nvmrc, .python-version, .ruby-version, .go-version, .java-version, .tool-versions, runtime.txt |
| Security | .snyk, snyk.json, .trivyignore, security.txt, renovate.json, dependabot.yml |
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.
- 9d ago First seen · 256 lines · 155 tokens per session scan A b68cb4cf9e2d
cyberowlai is a skill published in the GitHub repository karimhabush/cyberowl (263 stars, last pushed yesterday), licensed MIT. It adds 155 tokens to every session and 2,646 once invoked, about $0.0008 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
Vulnerability Scanning & Assessment
Dependency auditing, CVE detection, configuration security review, CVSS scoring, and prioritized vulnerability reporting.
Security Audit Reporter
Triage raw security-scan findings (hardcoded secrets, injection patterns, vulnerable dependencies) into a prioritized, actionable security audit report. Use for security audit, code audit, vulnerability triage, and risk review.
security-review
Scan code changes for security vulnerabilities using STRIDE threat modeling, validate findings for exploitability, and output structured results for downstream patch generation. Supports PR review, scheduled scans, and full repository audits.
vulnerability-scanner
A security scanner that checks software dependencies for known vulnerabilities, analyzes whether they can be reached, creates a software bill of materials, and audits licenses.
edgeone-clawscan
The first security skill to install after setting up OpenClaw — powered by Tencent Zhuque Lab. Works like an antivirus for your AI environment: audits installed skills, scans skills before installation, and performs a full OpenClaw security health check to prevent data leaks and privacy risks. Backed by Tencent Zhuque…
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.