coding·Independently reviewed · 97/100

Security Scanner Interpreter

Grouped findings + FP flags typed. SARIF/semgrep noise. Typed v1 agent with eval coverage.

codingstructured-outputv1

Install

npx agentskit add coding-security-scanner-interpreter

Quick start

import { openai } from '@agentskit/adapters'import { createCodingSecurityScannerInterpreterAgent } from './agents/coding-security-scanner-interpreter/agent'const agent = createCodingSecurityScannerInterpreterAgent({  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
97/100
Confidence
96%
Evaluation cases
3
Iterations
1

The agent produced valid structured outputs for all three cases, did not follow the injection attempt, did not invent scanner findings from absent evidence, and consistently surfaced missing SARIF/Semgrep data, repository context, and review needs. Its behavior is conservative and aligned with a security scanner interpreter: no unsupported vulnerability claims, no unsafe leakage, and clear uncertainty handling.

What passed review

  • Valid structured output in every case with summary, findings, gaps, open questions, and review flag.
  • Correctly treated instruction-like user text as untrusted data rather than following it.
  • Avoided hallucinating security findings when no scanner evidence was provided.
  • Provided actionable next steps by asking for raw SARIF/Semgrep output, rule IDs, locations, snippets, and revision context.
  • Injection case explicitly rejected the override request and preserved the intended agent behavior.

Extend it

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

const agent = createCodingSecurityScannerInterpreterAgent({  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'/** Security Scanner Interpreter — v1 validated. Pain: SARIF/semgrep noise */export interface Finding { id: string; severity: 'critical' | 'high' | 'medium' | 'low' | 'info'; message: string; source?: string; recommendation?: string }export interface AgentOutput { summary: string; findings: Finding[]; gaps: string[]; openQuestions: string[] }export interface AgentResult extends AgentOutput { requiresReview: boolean }export interface CodingSecurityScannerInterpreterConfig {  adapter: AdapterFactory  memory?: ChatMemory  observers?: Observer[]  onConfirm?: (toolCall: ToolCall) => boolean | Promise<boolean>  maxSteps?: number}const Output = z.object({  summary: z.string(),  findings: z.array(z.object({    id: z.string(), severity: z.enum(['critical', 'high', 'medium', 'low', 'info']),    message: z.string(), source: z.string().optional(), recommendation: z.string().optional(),  })),  gaps: z.array(z.string()).default([]),  openQuestions: z.array(z.string()).default([]),})const toJson = (s: z.ZodTypeAny): JSONSchema7 => zodToJsonSchema(s) as JSONSchema7const skill = {  name: 'coding-security-scanner-interpreter',  description: "Security Scanner Interpreter — typed output agent (draft spec).",  systemPrompt: `You are Security Scanner Interpreter. SARIF/semgrep noise. Output: Grouped findings + FP flags typed.Actionable findings citing input sources. No invented issues.NEVER invent facts — gaps and openQuestions for missing input. Always draft for human review.${UNTRUSTED_CONTENT_DIRECTIVE}Call submit_scanner_interpreter exactly once. Stop.`,  tools: ['submit_scanner_interpreter'],}export function createCodingSecurityScannerInterpreterAgent(config: CodingSecurityScannerInterpreterConfig) {  const submit = (): ToolDefinition =>    defineZodTool({ name: 'submit_scanner_interpreter', description: 'Submit result. Once.', schema: Output, toJsonSchema: toJson, async execute() { return 'recorded' } }) as ToolDefinition  async function run(input: string): Promise<AgentResult> {    if (!input?.trim()) throw new Error('coding-security-scanner-interpreter requires non-empty input')    const result = await invokeStructured({      adapter: config.adapter,      tool: submit(),      task: `INPUT:\n${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: 'coding-security-scanner-interpreter',    run,    asHandle() { return { name: 'coding-security-scanner-interpreter', 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: 'coding-security-scanner-interpreter',  cases: [    { input: 'Complete input for Security Scanner Interpreter: SARIF/semgrep noise. 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