SkillTotal

Is @openai/agents-core safe?

No malicious indicators - review capabilities before installing
Notable — review in context (capabilities are not malware):
  • Node.js shell/command execution
  • Node.js network egress

@openai/agents-core is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 2 risky constructs are reported for review. It can: network egress and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

@openai/agents-core 0.18.0

npm_package · npm:@openai/agents-core
LOW
0
/ 100 risk score
Snapshot · scanned Sep 24, 2026 · @openai/agents-core@0.18.0 · engine 0.53.0 / ruleset 60

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of @openai/agents-core's authors. Report a false positive.

Capabilities — what this component can do (not a risk score):
network egressshell execution

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Execution authority
Tool Access Control / Direct Tool Access
Network egress
Interaction & Communication / Direct Communication

Findings (2)

HIGHNode.js shell/command executionST-SHELL-NODE

The component can run operating-system commands or spawn processes.

import { type ChildProcessWithoutNullStreams } from 'node:child_process';
const node_child_process_1 = require("node:child_process");
import { spawn } from 'node:child_process';
return spawn('docker', dockerArgs, {
const child = spawn('docker', args, {
import { type ChildProcessWithoutNullStreams } from 'node:child_process';
const node_child_process_1 = require("node:child_process");
import { spawn, spawnSync, } from 'node:child_process';
return spawn(pythonExecutable, ['-c', PTY_BRIDGE_SCRIPT, executable, ...args], {
const result = spawnSync(pythonExecutable, ['-c', PTY_BRIDGE_PYTHON_CHECK_SCRIPT], {
const node_child_process_1 = require("node:child_process");
import { spawn } from 'node:child_process';
const child = spawn(command, args, {
const node_child_process_1 = require("node:child_process");
import { spawn, spawnSync } from 'node:child_process';
const child = spawn(this.executable, ['-I', '-S', '-c', UNIX_LOCAL_FILE_WORKER, JSON.stringify(request)], {
import { type ChildProcessWithoutNullStreams } from 'node:child_process';
exec(args: ExecCommandArgs): Promise<SandboxExecResult>;
const node_child_process_1 = require("node:child_process");
import { spawn } from 'node:child_process';
return spawn(shellPath, [flag, command], {

Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.

Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; prefer execFile with an argument array.

MEDIUMNode.js network egressST-NET-NODE

The component makes outbound network requests.

const response = await fetch(options.endpoint, {
const response = await fetch(options.endpoint, {

Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.

Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →