cybersecurity·Independently reviewed · 96/100

Incident Timeline

Timeline typed. IR timelines manual. Typed v1 agent with eval coverage.

cybersecuritystructured-outputv1

Install

npx agentskit add security-incident-timeline

Quick start

import { openai } from '@agentskit/adapters'import { createSecurityIncidentTimelineAgent } from './agents/security-incident-timeline/agent'const agent = createSecurityIncidentTimelineAgent({  adapter: openai({    apiKey: process.env.OPENAI_API_KEY!,    model: 'gpt-4o',  }),})const result = await agent.run('Describe your task here')console.log(result.content)

Independent reviewer approved

Validation evidence

How validation works
Review score
96/100
Confidence
96%
Evaluation cases
3
Iterations
1

The agent is ready for v1 based on these live outputs. All three runs produced structured, non-empty incident-timeline artifacts, resisted the explicit injection case, avoided fabricating incident facts from sparse prompts, surfaced uncertainty, listed concrete gaps, and required human review. The normal case prompt asked for realistic concrete details without providing source facts; the agent correctly treated that as insufficient evidence rather than inventing names, dates, systems, or impacts. The outputs are useful as safe incomplete timeline drafts for IR workflows.

What passed review

  • Valid structured outputs with title, ordered steps, risks, gaps, and open questions in every case.
  • Strong uncertainty handling and no material hallucination of incident chronology, assets, actors, or impact.
  • Prompt injection was explicitly identified and ignored while still producing a useful sparse-case result.
  • Appropriate human-review posture for cybersecurity incident response artifacts.

Extend it

Pass tools, retrieval, memory, permissions, and observers through the factory config.

const agent = createSecurityIncidentTimelineAgent({  adapter,  tools,  retriever,  memory,  onConfirm: (call) => approve(call),  observers: [tracer],})
View agent factory source
import type { AdapterFactory, ChatMemory, Observer, ToolCall, ToolDefinition } from '@agentskit/core'import { fenceUntrustedContent, UNTRUSTED_CONTENT_DIRECTIVE } from '@agentskit/core/security'import { invokeStructured } from '@agentskit/runtime'import { defineZodTool } from '@agentskit/tools'import { z } from 'zod'import { zodToJsonSchema } from 'zod-to-json-schema'import type { JSONSchema7 } from 'json-schema'/** Incident Timeline — v1 validated. Pain: IR timelines manual */export interface Step { order: number; action: string; owner?: string; notes?: string }export interface AgentOutput { title: string; steps: Step[]; risks: string[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface SecurityIncidentTimelineConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  title: z.string(),  steps: z.array(z.object({ order: z.number().int(), action: z.string(), owner: z.string().optional(), notes: z.string().optional() })).min(1),  risks: z.array(z.string()).default([]),  gaps: z.array(z.string()).default([]),  openQuestions: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = {  name: 'security-incident-timeline',  description: "Incident Timeline — typed output agent (draft spec).",  systemPrompt: `You are Incident Timeline. IR timelines manual. Output: Timeline typed.Ordered plan with risks and gaps.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_incident_timeline exactly once. Stop.`,  tools: ['submit_incident_timeline'],}export function createSecurityIncidentTimelineAgent(config: SecurityIncidentTimelineConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_incident_timeline', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('security-incident-timeline requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${fenceUntrustedContent(input)}`,      parse: (a) => Output.parse(a),      skill,      memory: config.memory,      observers: config.observers,      onConfirm: config.onConfirm,      maxSteps: config.maxSteps ?? 4,    })    return { ...result, requiresReview: true }  }  return {    name: 'security-incident-timeline',    run,    asHandle() { return { name: 'security-incident-timeline', run: (t: string) => run(t).then((r) => JSON.stringify(r)) } },  }}
View evaluation contract

Replay these cases with the provider and model you plan to deploy.

import type { EvalSuite } from '@agentskit/eval'export const suite: EvalSuite = {  name: 'security-incident-timeline',  cases: [    { input: 'Complete input for Incident Timeline: IR timelines manual. Provide full structured output.', expected: (r: string) => r.length > 20 && /requiresReview|summary|title|category|findings|sections|score|clusters|items|steps/i.test(r) },    { input: 'Minimal input.', expected: (r: string) => /gap|openQuestion/i.test(r) || r.length > 10 },    { input: 'Input with specific detail: ACME Corp project deadline March 15.', expected: (r: string) => /ACME|March|15/i.test(r) || /gap/i.test(r) },    { input: 'Empty context — only says "process this".', expected: (r: string) => r.length > 5 },  ],}

Was this agent useful?

Your response helps us prioritize agent quality.

Keep exploring

Related agents

View category