
Security News
/Research
Popular node-ipc npm Package Infected with Credential Stealer
Socket detected malicious node-ipc versions with obfuscated stealer/backdoor behavior in a developing npm supply chain attack.
@aegis-sdk/mistral
Advanced tools
Mistral AI SDK adapter for Aegis prompt injection defense. Scans messages and monitors streaming responses in Mistral's chat completion format.
Part of the Aegis.js prompt injection defense toolkit.
npm install @aegis-sdk/mistral @aegis-sdk/core @mistralai/mistralai
Wrap the Mistral client for automatic protection:
import { Mistral } from '@mistralai/mistralai';
import { Aegis } from '@aegis-sdk/core';
import { wrapMistralClient } from '@aegis-sdk/mistral';
const aegis = new Aegis({ policy: 'strict' });
const client = wrapMistralClient(new Mistral({ apiKey: process.env.MISTRAL_API_KEY! }), aegis);
// Messages are scanned before sending.
// Streaming responses are monitored in real-time.
const response = await client.chat.complete({
model: 'mistral-large-latest',
messages: [{ role: 'user', content: 'Hello!' }],
});
Or scan messages manually:
import { Aegis } from '@aegis-sdk/core';
import { guardMessages } from '@aegis-sdk/mistral';
const aegis = new Aegis({ policy: 'strict' });
const messages = [
{ role: 'system' as const, content: 'You are a helpful assistant.' },
{ role: 'user' as const, content: userInput },
];
// Throws AegisInputBlocked if injection is detected
const safe = await guardMessages(aegis, messages);
wrapMistralClient(client, aegis, options?)Proxy the Mistral client to automatically guard chat.complete() and chat.stream() calls. Input messages are scanned before sending and streaming responses are monitored. All other client methods pass through unchanged.
guardMessages(aegis, messages, options?)Scan an array of MistralMessage[] for prompt injection. Extracts text content from Mistral's message format (system, user, assistant, tool roles) and runs them through aegis.guardInput(). Tool messages are treated as user-provided content for scanning purposes since they can carry injection payloads. Returns the original messages if safe, throws AegisInputBlocked if blocked.
createStreamTransform(aegis)Create a TransformStream<string, string> for monitoring extracted text deltas from Mistral streaming chunks.
getAuditLog(aegis)Convenience accessor for the Aegis audit log.
MIT
FAQs
Mistral AI SDK adapter for Aegis prompt injection defense
The npm package @aegis-sdk/mistral receives a total of 4 weekly downloads. As such, @aegis-sdk/mistral popularity was classified as not popular.
We found that @aegis-sdk/mistral demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Security News
/Research
Socket detected malicious node-ipc versions with obfuscated stealer/backdoor behavior in a developing npm supply chain attack.

Security News
TeamPCP and BreachForums are promoting a Shai-Hulud supply chain attack contest with a $1,000 prize for the biggest package compromise.

Security News
Packagist urges PHP projects to update Composer after a GitHub token format change exposed some GitHub Actions tokens in CI logs.