security-disclosure-triage

Official

Triages advisories to separate real flaws.

Authorsuperagent-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Verify whether an incoming security advisory is a real, disclosable vulnerability in a target repository checkout, and assign an honest severity. Use when triaging an advisory, GHSA, scanner finding, or draft report from the researcher/reporter side to decide if it is worth disclosing. Optimizes against false confirmations and inflated severity.

Core Features & Use Cases

  • Reproduces the advisory construct to determine if it maps to a real vulnerability.
  • Identifies the crown-jewel asset and the actual guard, reducing false positives.
  • Produces structured triage outputs and a recommended disposition with severity calculations.
  • Use Case: A security team receives a GHSA draft, and this skill guides evaluation from reproduction to disclosure decision.

Quick Start

Follow the triage framework to assess a new advisory against a target repository checkout and produce a triage report.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: security-disclosure-triage
Download link: https://github.com/superagent-ai/skills/archive/main.zip#security-disclosure-triage

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.