Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Agentic capability / OpenAI Agents SDK
◉AgentAgentic capabilityFree

OpenAI Agents SDK

OpenAI's lightweight Python framework for building multi-agent systems with handoffs, tracing, and guardrails.

@ai-supply
Installs364k
⟳ upstream v0.18.3 · updated 10d ago
↗ Source repository
← More Agentic capabilityAgentic capability leaderboard →How we grade security →Source ↗
! Grade B · 75/100 · ReviewSecurity assessment
✓No compromise signals27capabilities surfaced1known CVE8of 20 OWASP controls clear
Broad capability surfaceBroad capability surfacePotentially unbounded loopSuspicious network references
scanned 8d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

OpenAI Agents SDK

The OpenAI Agents SDK (formerly Swarm) is a production-ready, MIT-licensed Python framework for building agentic applications. It ships with primitives for tool calling, agent handoffs, input/output guardrails, and a powerful tracing UI — plus first-class support for any model via the OpenAI-compatible API.

Key Features

  • Agents: define agents as a model + system prompt + list of tools + optional handoff targets
  • Handoffs: cleanly transfer control (and context) between specialised agents in a pipeline
  • Tool calling: any Python function decorated with @function_tool becomes a callable tool
  • Guardrails: input and output validators run in parallel to the agent for fast rejection
  • Tracing: built-in OpenAI dashboard traces every step — LLM call, tool call, handoff
  • MCP support: mount any MCP server as a tool source without extra glue code

Quick Start

pip install openai-agents
from agents import Agent, Runner, function_tool

@function_tool
def get_weather(city: str) -> str:
    return f"Sunny and 22°C in {city}"

agent = Agent(
    name="Weather Bot",
    instructions="Answer questions about weather using the provided tool.",
    tools=[get_weather],
)

result = Runner.run_sync(agent, "What's the weather in Berlin?")
print(result.final_output)
npx ai-supply add openai-agents-python-sdk

Curated mirror of the open-source OpenAI Agents SDK (MIT). Get it from the source.

Rating rank
#1
of 35 in Agentic capability
Install rank
#5
of 35 in Agentic capability
Security score
75/100 · B
review
Security rank
#23
of 35 in Agentic capability
Installs
364k
cat avg 186k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Agentic capability leaderboard →
! Security: Review · 7575/100 · grade Bscanned 8d ago
✓ no compromise signals28 risk-surface · 7/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · high confidence (static)
Tools (5)
addechoget_secret_wordget_current_weatherprocess_user
⚑ filesystem⚑ shell⚑ network⚑ secrets
egress → developers.openai.com, openai.github.io, api.github.com, pypi.org, go.microsoft.com, img.shields.io, cdn.openai.com, docs.astral.sh +32

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 5 pip requirements declared · openai-openai-agents-python-173eca4/examples/realtime/twilio/requirements.txtrisk surface
•Dependency manifest — 3 pip requirements declared · openai-openai-agents-python-173eca4/examples/realtime/twilio_sip/requirements.txtrisk surface
•Vulnerable dependencies — 148 known vulnerabilities in: aiohttp@3.12.15, cbor2@5.8.0, click@8.2.1, cryptography@45.0.7, filelock@3.18.0, idna@3.10, litellm@1.83.0, mcp@1.26.0 (CWE-1395)known CVE · -25 pts
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — OS command execution · openai-openai-agents-python-173eca4/.agents/skills/runtime-behavior-probe/templates/python_probe.py (CWE-78)expected
•Suspicious code patterns — python reverse shell; OS command execution · openai-openai-agents-python-173eca4/examples/mcp/manager_example/smoke_test.py (CWE-78)expected
•Suspicious code patterns — destructive rm -rf /; pipe-to-shell install · openai-openai-agents-python-173eca4/examples/sandbox/docker/Dockerfile.mount (CWE-78)expected
•Suspicious code patterns — dynamic code execution · openai-openai-agents-python-173eca4/examples/sandbox/docs/coding_task.py (CWE-95)expected
•Suspicious code patterns — destructive rm -rf / · openai-openai-agents-python-173eca4/examples/sandbox/tutorials/Dockerfile (CWE-78)expected
•Suspicious code patterns — pipe-to-shell install; dynamic code execution · openai-openai-agents-python-173eca4/src/agents/extensions/sandbox/_rclone.py (CWE-494)expected
•Suspicious code patterns — pipe-to-shell install · openai-openai-agents-python-173eca4/tests/extensions/sandbox/test_e2b.py (CWE-494)expected
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · openai-openai-agents-python-173eca4/.agents/references/conversation-state-ownership.mdexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · openai-openai-agents-python-173eca4/.agents/references/sandbox-runtime-boundary.md (CWE-272)risk surface
•External endpoints declared — 7 distinct host(s) · openai-openai-agents-python-173eca4/README.mdexpected
•External endpoints declared — 2 distinct host(s) · openai-openai-agents-python-173eca4/SECURITY.mdexpected
•External endpoints declared — 3 distinct host(s) · openai-openai-agents-python-173eca4/docs/agents.mdexpected
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege · openai-openai-agents-python-173eca4/docs/examples.md (CWE-272)risk surface
•External endpoints declared — 4 distinct host(s) · openai-openai-agents-python-173eca4/docs/ja/mcp.mdexpected
•External endpoints declared — 12 distinct host(s) · openai-openai-agents-python-173eca4/docs/ja/running_agents.mdexpected
•External endpoints declared — 30 distinct host(s) · openai-openai-agents-python-173eca4/docs/ja/tracing.mdexpected
•Egress to a private/loopback host — 127.0.0.1 · openai-openai-agents-python-173eca4/examples/mcp/manager_example/README.md (CWE-918)expected
•Egress to an anonymous-paste / tunnel / OOB endpoint — abc123.ngrok.io, your-ngrok-url.ngrok.io · openai-openai-agents-python-173eca4/examples/realtime/twilio/README.md (CWE-200)expected
•External endpoints declared — 5 distinct host(s) · openai-openai-agents-python-173eca4/examples/realtime/twilio/README.mdexpected
•External endpoints declared — 11 distinct host(s) · openai-openai-agents-python-173eca4/tests/extensions/sandbox/test_blaxel.pyexpected
⚠LLM07System Prompt Leakagemedium
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · openai-openai-agents-python-173eca4/examples/sandbox/docker/mounts/s3_files_mount_read_write.py (CWE-200)risk surface
⚠LLM10Unbounded Consumptionmedium
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · openai-openai-agents-python-173eca4/docs/ja/running_agents.md (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM01Prompt InjectionPassed
✓LLM02Sensitive Information DisclosurePassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML06AI Supply Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 5 pip requirements declared · openai-openai-agents-python-173eca4/examples/realtime/twilio/requirements.txtrisk surface
•Dependency manifest — 3 pip requirements declared · openai-openai-agents-python-173eca4/examples/realtime/twilio_sip/requirements.txtrisk surface
•Vulnerable dependencies — 148 known vulnerabilities in: aiohttp@3.12.15, cbor2@5.8.0, click@8.2.1, cryptography@45.0.7, filelock@3.18.0, idna@3.10, litellm@1.83.0, mcp@1.26.0 (CWE-1395)known CVE · -25 pts
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — OS command execution · openai-openai-agents-python-173eca4/.agents/skills/runtime-behavior-probe/templates/python_probe.py (CWE-78)expected
•Suspicious code patterns — python reverse shell; OS command execution · openai-openai-agents-python-173eca4/examples/mcp/manager_example/smoke_test.py (CWE-78)expected
•Suspicious code patterns — destructive rm -rf /; pipe-to-shell install · openai-openai-agents-python-173eca4/examples/sandbox/docker/Dockerfile.mount (CWE-78)expected
•Suspicious code patterns — dynamic code execution · openai-openai-agents-python-173eca4/examples/sandbox/docs/coding_task.py (CWE-95)expected
•Suspicious code patterns — destructive rm -rf / · openai-openai-agents-python-173eca4/examples/sandbox/tutorials/Dockerfile (CWE-78)expected
•Suspicious code patterns — pipe-to-shell install; dynamic code execution · openai-openai-agents-python-173eca4/src/agents/extensions/sandbox/_rclone.py (CWE-494)expected
•Suspicious code patterns — pipe-to-shell install · openai-openai-agents-python-173eca4/tests/extensions/sandbox/test_e2b.py (CWE-494)expected
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (11) · hygiene / uncategorized
•Disallowed file type — '.ps1' executables are not permitted · openai-openai-agents-python-173eca4/.agents/skills/code-change-verification/scripts/run.ps1 (CWE-434)risk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · openai-openai-agents-python-173eca4/.gitignorerisk surface
•Unrecognized file type — '.prettierrc' is not on the allowlist · openai-openai-agents-python-173eca4/.prettierrcrisk surface
•Unrecognized file type — '.?' is not on the allowlist · openai-openai-agents-python-173eca4/LICENSErisk surface
•Suspicious network references — raw IP URL (9 URLs) · openai-openai-agents-python-173eca4/examples/mcp/manager_example/README.mdrisk surface
•Suspicious network references — raw IP URL (1 URLs) · openai-openai-agents-python-173eca4/examples/run_examples.pyrisk surface
•Unrecognized file type — '.mount' is not on the allowlist · openai-openai-agents-python-173eca4/examples/sandbox/docker/Dockerfile.mountrisk surface
•Unrecognized file type — '.typed' is not on the allowlist · openai-openai-agents-python-173eca4/src/agents/py.typedrisk surface
•Suspicious network references — raw IP URL (12 URLs) · openai-openai-agents-python-173eca4/tests/models/test_openai_responses.pyrisk surface
•Suspicious network references — raw IP URL (5 URLs) · openai-openai-agents-python-173eca4/tests/sandbox/test_exposed_ports.pyrisk surface
•Suspicious network references — raw IP URL (4 URLs) · openai-openai-agents-python-173eca4/tests/test_trace_processor.pyrisk surface
✔ verified source · pinned openai-openai-agents-python-173eca4
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/openai-agents-python-sdk/check). Click a policy:

Consume OpenAI Agents SDK programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/openai-agents-python-sdk

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/openai-agents-python-sdk/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add openai-agents-python-sdk

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/openai-agents-python-sdk/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "openai-agents-python-sdk" })
OpenAPI spec →
vlatest
! Security: Review · 751mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
  • Scan a repo
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy