
Security News
Anthropic Identifies Biased Reasoning and Recklessness as Drivers of Claude’s PyPI Attack
Anthropic found biased reasoning and recklessness drove Claude Mythos 5 to publish malware on PyPI and compromise a security vendor.
npm install trigguard
import { TrigGuard, TrigGuardError } from "trigguard";
const tg = new TrigGuard();
const receipt = {
decision: "PERMIT",
timestamp: new Date().toISOString(),
};
try {
const result = await tg.verify.receipt(receipt);
console.log(result.valid, result);
} catch (err) {
if (err instanceof TrigGuardError) {
console.error(err.code, err.message, err.request_id);
}
throw err;
}
Install → construct client → call → handle TrigGuardError predictably.
npm install trigguard
From a git clone:
npm install ./path/to/trigguard-js
const tg = new TrigGuard({
authority: "https://trigguardai.com",
});
You can also pass a string shorthand: new TrigGuard("https://your-authority.example").
Environment fallbacks (Node): TRIGGUARD_AUTHORITY or TRIGGUARD_BASE_URL when no constructor argument is given.
curl (no install)curl -sS https://trigguardai.com/protocol/test-vectors | head
curl -sS -X POST https://trigguardai.com/protocol/verify-receipt \
-H "Content-Type: application/json" \
-d '{"decision":"PERMIT","timestamp":"2026-01-01T00:00:00.000Z"}'
node examples/verify-receipt.js
| Member | Description |
|---|---|
new TrigGuard(options?) | Client; default authority https://trigguardai.com |
tg.authority | Resolved origin (no trailing slash) |
tg.verify.receipt(body) | POST /protocol/verify-receipt |
tg.verify.signature(body) | POST /protocol/verify-signature |
tg.protocol.capabilities() | GET /protocol/capabilities |
Failures throw TrigGuardError (extends Error):
err.code — machine-readable (from API when present, else HTTP_ERROR / NETWORK_ERROR)err.message — human-readableerr.request_id — when the authority returns oneerr.status — HTTP status when applicableerr.body — parsed JSON body when availableerr.toJSON() — stable shape for logsTrigGuard is execution-governance infrastructure: deterministic PERMIT / DENY / SILENCE before irreversible actions, with verifiable receipts. This package is a small HTTP client for the public protocol endpoints. Policy evaluation lives in authority / hosted services — not in this SDK.
@trigguard/protocolFAQs
TrigGuard public SDK — authorize, verify, receipts, agents, CLI. One install.
The npm package trigguard receives a total of 162 weekly downloads. As such, trigguard popularity was classified as not popular.
We found that trigguard 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.

Security News
Anthropic found biased reasoning and recklessness drove Claude Mythos 5 to publish malware on PyPI and compromise a security vendor.

Research
/Security News
Malicious Chrome and Firefox extensions target Axiom Trade and Padre users, stealing session tokens and wallet data.

Security News
GPT-6 Astra hits 100% on ExploitBench and finds zero-days autonomously, while independent tests reveal scope violations and monitoring gaps.