Is @openai/agents-realtime safe?

No malicious indicators - review capabilities before installing

Notable — review in context (capabilities are not malware):

Node.js network egress

What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.

@openai/agents-realtime is an npm package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

@openai/agents-realtime 0.19.0

npm_package · npm:@openai/agents-realtime

LOW

/ 100 risk score

Snapshot · scanned Oct 7, 2026 · @openai/agents-realtime@0.19.0 · engine 0.56.2 / ruleset 62

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

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

network egress

Behavioral traits

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

Network egress

Interaction & Communication / Direct Communication

Findings (1)

MEDIUMNode.js network egressST-NET-NODE

The component makes outbound network requests.

dist/openaiRealtimeWebRtc.js:399-399

const sdpResponse = await fetch(connectionUrl, {

dist/openaiRealtimeWebRtc.mjs:393-393

const sdpResponse = await fetch(connectionUrl, {

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 →