agentleFS
Sign inStart free
AdriDobAdriDob/OWNEX/skills/ownex-security/SKILL.md

ownex-security

Skill1 starsChanged 3 months agoMITView on GitHub

Goal: Daily vulnerability triage — scan new findings, validate evidence, prioritize by severity, and escalate critical items. App: cateye · Cadence: 1d · Risk: high report → discover → triage → classify → act → notify

The file

Create a free account to mount
Files
SKILL.md

OWNEX Security Cycle — Security Triage

Goal: Daily vulnerability triage — scan new findings, validate evidence, prioritize by severity, and escalate critical items.

App: cateye · Cadence: 1d · Risk: high

Default Phases

report → discover → triage → classify → act → notify

Human Gates

  • Critical-severity findings (require human confirmation)
  • Payout decisions
  • Program boundary decisions (scope edge cases)

Required Skills

  • loop-triage — General triage capability
  • evidence-quality — Score evidence completeness per finding
  • report-draft — Draft validation reports for confirmed findings
  • priority-score — Compute CVSS + context priority

State File

# Security Cycle State
Last run: <timestamp>
High Priority:
  - F-001: Critical RCE in auth endpoint — awaiting human review
Watch List:
  - F-003: Medium XSS — 48h without action
Recent Noise:
  - F-004: False positive (WAF bypass, tested negative)

Success Metrics

  • Time from finding creation to triage
  • % of findings validated vs rejected
  • Payout rate from triaged findings
  • False positive rate reduction

Budget

  • Daily cap: 100k tokens
  • Max runs: 2/day
  • L1: report only (first week)
  • L2: auto-draft reports (after quality validation)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free