Who it is for
The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows in JavaScript/TypeScript. It is provider-agnostic, supporting OpenAI APIs and more.
README.md:5
PUBLIC REPORT / AGENT SIGNAL v0.2
openai-agents-js.
Scanned repository says: The OpenAI Agents SDK is a lightweight yet powerful framework for building multi-agent workflows in JavaScript/TypeScript. It is provider-agnostic, supporting OpenAI APIs and more.
Inspect GitHub source0community interest
Votes show community interest, not safety. They never change this score.
76/100BBBNot security certification
Critical findings need attention.
Critical finding · details withheld for 30 days
Inspect the findingsRuntime safety, real-world agent capability, fitness for your use case or independent certification.
Scan scope80 / 849Partial eligible-file selection · not the entire repository
Recorded findings7Heuristic matches requiring human review
SnapshotOct 9, 2026UTC · engine 0.2.0
DNS at scan timeUnverifiedDomain control is not security certification
What the source
actually tells us.
Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.
80 / 849Partial selection
ReadRepository-authored information
2LICENSE, package.json
What it can do
Agents: LLMs configured with instructions, tools, guardrails, and handoffs
README.md:11Sandbox Agents: Agents paired with a filesystem workspace and sandbox environment for longer-running work
README.md:12Realtime Agents: Low-latency agents for spoken interactions, with tools, guardrails, handoffs, and conversation history
README.md:13
What adoption takes
No matching setup or dependency statement was extracted from inspected metadata.
Limits and terms
A license or copying file is present; its terms have not been reviewed.
LICENSE:1
Observed technical context
TypeScript · 80 selected filesModel API reference · static onlyTool-calling reference · static only
These are references in selected source files, not proof that a feature works at runtime.
Observed in the scanned archive at Oct 9, 2026, 2:20 PM UTC. Archive digest sha256:49568d597284e3fc…. Source links open current GitHub HEAD and may differ from the scan. Repository statements are unreviewed and do not affect the score.
02 / FINDINGS FIRSTWhat needs
What needs
a closer look.
Critical details are withheld publicly for the first 30 days after a scan. A matched pattern is a lead for investigation, not a confirmed vulnerability.
7 findings
CRITICALCritical finding · details withheld for 30 days
Critical finding · details withheld for 30 days
Details are withheld from public view for 30 days after the scan. The owner can see them in full.
Review the private assessment and address the finding.
MAJORLLM request without token ceiling
LLM request without token ceiling
A model request does not set a maximum output length. One unusual input can produce a very long, expensive response.
Set max_tokens or the provider's equivalent on each model call.
MAJORLLM output without runtime schema
LLM output without runtime schema
Model output is used without being checked against a schema. Unexpected or malformed output can break later steps or be trusted when it should not be.
Validate model output with Zod, JSON Schema, Pydantic or provider structured output.
MAJORModel call without fallback
Model call without fallback
A model call has no visible fallback. If the provider fails or is rate limited, the whole agent fails with it.
Configure a secondary model or explicit fallback path for provider failures.
MAJORDomain ownership not verified
Domain ownership not verified
Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.
Verify the domain using the Metal Mantra DNS TXT challenge.
MINORPrivacy Policy link not confirmed
Privacy Policy link not confirmed
No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.
Expose a clear Privacy Policy link on the official homepage.
MINORTerms link not confirmed
Terms link not confirmed
No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.
Expose a clear Terms link on the official homepage.
The boundary
is part of the result.
- What was scanned
- 80 of 849 eligible files · Partial selection.
Supported static source patterns and domain checks; no runtime execution. - What remains unknown
- Unscanned files, external dependencies, production configuration, actual agent behavior and evidence beyond the configured checks.
- Source location
- Links open the current repository HEAD. Source may have changed since this snapshot.
- Something looks wrong?
- Tell us if a finding, scope or claim on this report needs a correction. Report a problem with this report
- Entity trust · 15% of v0.2
- Includes DNS ownership, HTTPS and policy evidence. Verification is domain control, not a security certificate.DNS: unverifiedHTTPS: availablePrivacy: not confirmedTerms: not confirmed
Open the
calculation.
Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.
Security & privacy
82/100
Guardrails & loop control
88/100
Schema & tooling
84/100
Token & cost efficiency
86/100
Entity trust
25/100
Did openai-agents-js work for people?
No user reports yet.
Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.
SHARE THE EVIDENCEA signal.
A signal.
Not a seal.
Share the full report so its scope and limits travel with the score.
