CyberOwl AI skill
CyberOwl AI matches security advisories against your project dependencies and tells you which alerts actually affect you
- 264 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The skill is downloaded from an external site and holds instructions for the agent; read it before running.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/cyberowl-aiDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The skill is downloaded from an external site and holds instructions for the agent; read it before running.
This is third-party code. Review the repository files before installing.
What it does
The project collects security advisories from ten sources: US-CERT (CISA), CERT-FR, EU-CERT, HK-CERT, CA-CCS, MA-CERT, OBS Vigilance, IBM X-Force, ZeroDayInitiative and VulDB. Scrapy spiders run daily in GitHub Actions and write `alerts.json` and activity pages. The `cyberowlai` skill downloads `alerts.json`, inspects project dependencies, Dockerfiles, CI configuration and infrastructure, and matches them to advisories. Invoke it with `/cyberowlai` or ask "any security alerts for my project?".
Who it is for. Developers and small teams without a security department who need to learn quickly whether a fresh vulnerability touches their stack.
Good fit when
- A loud vulnerability appears and you must learn whether your project is hit.
- Dependencies and images are checked weekly against fresh advisories.
- Before a release, CERT alerts are narrowed to those matching your stack.
- A feed of ten sources is too noisy to read by hand.
Not a fit when
- You need a scanner that finds vulnerabilities in your code: the skill works with advisories.
- The project is closed and forbids calls to external sites.
- You need a full CVE database with scores: sources are limited to ten sites.
Example request
/cyberowlai Check dependencies and the Dockerfile against last week's alerts and show only those that affect us.Limitations
Data comes from cyberowlai.com, where the agent fetches `alerts.json`; availability and completeness of the feed depend on that site and its scrapers. `SKILL.md` is installed with `curl` from the same site, so open and read it before use. The model performs the matching, so it can miss an affected component or take a name collision for a vulnerability, and the result should be checked against the original advisory. Coverage is limited to the ten listed CERTs and aggregators.
How to disable. Delete `.claude/skills/cyberowlai/SKILL.md` or `.cursor/rules/cyberowlai.md` from the project.
FAQ
Where do alerts come from?
From ten public CERT and aggregator sources collected daily by Scrapy spiders.
Is there an API without an agent?
Yes, the feed is available as JSON at `https://cyberowlai.com/alerts.json`.
Does it work with Cursor?
Yes, put the same file at `.cursor/rules/cyberowlai.md`.
How often is data updated?
The scrapers run daily through GitHub Actions.
How do I invoke the skill?
With `/cyberowlai` or a question such as "any security alerts for my project?".
Discussion
No questions or reviews yet.
Related
SkillsA Claude Code skill that audits a project against OWASP 2025 and CWE Top 25 and writes a prioritized report with fixes.
Cybersecurity Skills
Cybersecurity Skills for AI Agents
42 security skills for Claude Code, Cursor and Codex: code and cloud audits, authorization-gated pentesting and incident response
A skill for reviewing code for vulnerabilities against OWASP Top 10:2025, ASVS 5.0 and the 2026 lists for LLM and AI agent security
A security scanner for agent skills: finds prompt injection, data exfiltration and malicious code before you install
The SecKnowledge skill loads a web-vulnerability and AI-app risk knowledge base into an agent for security testing of a target.
A code security audit skill by Cloudflare: the agent runs recon, coverage-led hunting and independent verification of findings, then produces a structured repor
README in short
A daily CERT advisory aggregator and a skill that matches them to the project stack.