integrations / langchain-js

LangChain.js Integration

Use Attestd as a LangChain.js tool to give agents real-time CVE risk and supply chain integrity data. The tool returns structured, deterministic output — no CVSS score interpretation, no ambiguous text for the agent to parse.

The most important correctness concern: outsideCoverage is not a safety signal. An agent that treats AttestdUnsupportedProductError as “no known vulnerabilities” is wrong. Catch it and return an explicit unknown-risk response.

installation

Install

bash

npm install @attestd/sdk @langchain/core @langchain/openai langchain zod

tool definition

tool() definition

Use tool() from @langchain/core/tools with an explicit Zod schema. This gives the LLM a validated schema and gives you typed inputs. Instantiate Client once at module level and capture it in the closure — never instantiate inside the tool function.

attestd-tool.ts

import { tool } from '@langchain/core/tools';
import { z } from 'zod';
import { Client, AttestdUnsupportedProductError } from '@attestd/sdk';

// Instantiate once — captured in closure. Never instantiate inside the tool function.
const _client = new Client({ apiKey: process.env.ATTESTD_API_KEY! });

export const checkVulnerability = tool(
  async ({ product, version }) => {
    try {
      const result = await _client.check(product, version);
      return {
        outsideCoverage: false,
        riskState: result.riskState,
        activelyExploited: result.activelyExploited,
        patchAvailable: result.patchAvailable,
        fixedVersion: result.fixedVersion,
        supplyChainCompromised: result.supplyChain?.compromised ?? false,
      };
    } catch (err) {
      if (err instanceof AttestdUnsupportedProductError) {
        // Product is outside Attestd coverage. This is NOT a safety signal.
        return {
          outsideCoverage: true,
          riskState: null,
          message: `No Attestd coverage for '${product}'. Treat as unknown risk.`,
        };
      }
      throw err;
    }
  },
  {
    name: 'check_package_vulnerability',
    description:
      'Check whether a software package version has known CVE vulnerabilities ' +
      'or supply chain compromise. Use before deploying or recommending any ' +
      'software dependency. outsideCoverage=true means Attestd has no data — ' +
      'treat as unknown risk, not safe. ' +
      'Input: product slug (e.g. "nginx", "runc", "@bitwarden/cli") and exact version string.',
    schema: z.object({
      product: z.string().describe('Package slug, e.g. "nginx", "runc", "@bitwarden/cli"'),
      version: z.string().describe('Exact version string, e.g. "1.0.0"'),
    }),
  },
);

agent executor

Agent executor pattern

Use createToolCallingAgent with any function-calling LLM. The system prompt must state the deployment-blocking policy explicitly — the model cannot infer the correct behaviour from the tool description alone.

agent.ts

import { ChatOpenAI } from '@langchain/openai';
import { createToolCallingAgent, AgentExecutor } from 'langchain/agents';
import { ChatPromptTemplate } from '@langchain/core/prompts';
import { checkVulnerability } from './attestd-tool.js';

const llm = new ChatOpenAI({ model: 'gpt-4o-mini', temperature: 0 });

const prompt = ChatPromptTemplate.fromMessages([
  [
    'system',
    'You are a security-aware deployment assistant. ' +
    'Before approving any software dependency, check its vulnerability status ' +
    'using the check_package_vulnerability tool. ' +
    'Block deployment if riskState is "critical" or "high", or if ' +
    'supplyChainCompromised is true. ' +
    'outsideCoverage=true means unknown risk — state this explicitly, ' +
    'do not treat it as safe.',
  ],
  ['human', '{input}'],
  ['placeholder', '{agent_scratchpad}'],
]);

const agent = createToolCallingAgent({ llm, tools: [checkVulnerability], prompt });
const executor = new AgentExecutor({ agent, tools: [checkVulnerability] });

// Example: check two dependencies before a deploy
const response = await executor.invoke({
  input: 'Is it safe to deploy with runc 1.0.0 and @bitwarden/cli 2026.4.0?',
});
console.log(response.output);

async

Async support

The JS Client is natively async. Every client.check() call returns a Promise. There is no separate async client class — the tool function above already works correctly in any async context. Use await executor.invoke({...}) as shown.

full example

Full runnable example

Checks four dependencies. Two are blocked by CVE risk, one by supply chain compromise, one is approved.

security-agent.ts

import { tool } from '@langchain/core/tools';
import { z } from 'zod';
import { ChatOpenAI } from '@langchain/openai';
import { createToolCallingAgent, AgentExecutor } from 'langchain/agents';
import { ChatPromptTemplate } from '@langchain/core/prompts';
import { Client, AttestdUnsupportedProductError } from '@attestd/sdk';

const _client = new Client({ apiKey: process.env.ATTESTD_API_KEY! });

const checkVulnerability = tool(
  async ({ product, version }) => {
    try {
      const result = await _client.check(product, version);
      return {
        outsideCoverage: false,
        riskState: result.riskState,
        activelyExploited: result.activelyExploited,
        patchAvailable: result.patchAvailable,
        fixedVersion: result.fixedVersion,
        supplyChainCompromised: result.supplyChain?.compromised ?? false,
      };
    } catch (err) {
      if (err instanceof AttestdUnsupportedProductError) {
        return {
          outsideCoverage: true,
          riskState: null,
          message: `No Attestd coverage for '${product}'. Treat as unknown risk.`,
        };
      }
      throw err;
    }
  },
  {
    name: 'check_package_vulnerability',
    description:
      'Check whether a software package version has known CVE vulnerabilities ' +
      'or supply chain compromise. Use before deploying or recommending any ' +
      'software dependency. outsideCoverage=true means unknown risk, not safe. ' +
      'Input: product slug and exact version string.',
    schema: z.object({
      product: z.string().describe('Package slug, e.g. "nginx", "runc", "@bitwarden/cli"'),
      version: z.string().describe('Exact version string'),
    }),
  },
);

const llm = new ChatOpenAI({
  model: 'gpt-4o-mini',
  temperature: 0,
  apiKey: process.env.OPENAI_API_KEY,
});

const prompt = ChatPromptTemplate.fromMessages([
  [
    'system',
    'You are a security-aware deployment assistant. ' +
    'Check each dependency with check_package_vulnerability before approving. ' +
    'Block if riskState is critical or high, or if supplyChainCompromised is true. ' +
    'State outsideCoverage results explicitly. Do not treat them as safe.',
  ],
  ['human', '{input}'],
  ['placeholder', '{agent_scratchpad}'],
]);

const agent = createToolCallingAgent({ llm, tools: [checkVulnerability], prompt });
const executor = new AgentExecutor({ agent, tools: [checkVulnerability] });

const dependencies = [
  ['runc', '1.0.0'],
  ['litellm', '1.82.7'],
  ['@bitwarden/cli', '2026.4.0'],
  ['nginx', '1.27.4'],
];

const query =
  'Check these dependencies: ' +
  dependencies.map(([p, v]) => `${p}@${v}`).join(', ');

const response = await executor.invoke({ input: query });
console.log(response.output);

fields

Return fields

The tool returns these fields. Design agent branching logic around them.

Field	Semantics
`outsideCoverage`	true if Attestd has no data for this product. Not a safety signal — treat as unknown risk.
`riskState`	"critical" \| "high" \| "elevated" \| "low" \| "none" \| null (when outsideCoverage). Block on critical or high.
`activelyExploited`	true if in the CISA KEV catalog. Block regardless of riskState if true.
`patchAvailable`	true if a fixed version is known. Use with fixedVersion to tell the agent what to recommend.
`fixedVersion`	The earliest clean version, or null if no patch exists yet.
`supplyChainCompromised`	true if a malicious publish or security signal was detected on PyPI or npm. Block immediately — independent of riskState.