triage-finding

Triage existing security findings against a repository using static code evidence.

Updated May 4, 2026
One-click install
npx skills add https://github.com/antstanley/skills --skill triage-finding-antstanley
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: triage-finding
Source: https://github.com/antstanley/skills/tree/main/plugins/security/skills/triage-finding
Command: npx skills add https://github.com/antstanley/skills --skill triage-finding-antstanley

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Security teams accumulate noisy backlogs of findings from scanners, CVEs, advisories, bug bounty reports, and Jira/Linear tickets, and manually verifying whether each claim actually affects the current codebase is slow and inconsistent. ## Core Features & Use Cases - Static Evidence-Based Verdicts: Assigns one of three verdicts (confirmed, not_actionable, needs_review) per finding using source-to-sink tracing, reachability analysis, and SECURITY.md policy gates, without running any code. - Multi-Source Intake: Imports findings from GitHub code scanning, Dependabot alerts, security advisories, Jira, and Linear via REST or MCP connectors, normalizing them into a common triage record. - Exploitability Stack Ranking: Ranks confirmed and needs_review findings in separate priority queues and emits a machine-readable triage-finding/v0 JSON contract. - Use Case: A team imports 40 open Dependabot and code-scanning alerts from GitHub and receives a ranked, evidence-backed action queue showing which vulnerabilities are actually reachable in their shipped code. ## Quick Start Triage the open security findings from this GitHub repository and tell me which ones are confirmed exploitable in the current code.

Frequently Asked Questions about triage-finding

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I triage security findings from GitHub code scanning?

Supply the GitHub repository as owner/repo or a URL and choose code scanning as the source. The skill fetches open alerts via the GitHub REST API, normalizes them as SARIF-type findings, and statically verifies each against your local code.

How to triage Jira or Linear vulnerability tickets against my codebase?

Provide the Jira or Linear issue URLs, keys, or a search query. The skill retrieves ticket content through a configured MCP server, normalizes each issue as a scanner ticket, and assigns an evidence-backed verdict per finding.

Does this skill run exploits or dynamic validation to confirm vulnerabilities?

No, all triage is strictly static. It never runs tests, builds, applications, PoCs, or exploit checks; verdicts rely on source-to-sink tracing, reachability analysis, and repository security policy evidence.

What is the difference between confirmed and needs_review verdicts?

Confirmed requires static proof that the vulnerable condition is reachable and crosses a supported security boundary. Needs_review is used when provenance, control semantics, or boundary policy cannot be established statically, with the unresolved fact recorded as a proof gap.

Can this skill deduplicate or fix the findings it triages?

No, it keeps one result per supplied finding and never deduplicates. For confirmed findings it prepares a handoff prompt for the separate fix-finding skill, which runs only when the user explicitly asks.