Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Agentic capability / Ollama
⇄ConnectorAgentic capabilityFree

Ollama

Run large language models locally with a single command. OpenAI-compatible API for Llama, Mistral, Gemma, and more.

@ai-supply
Installs296k
⟳ upstream v0.32.4 · updated 1d ago
↗ Source repository
← More Agentic capabilityAgentic capability leaderboard →How we grade security →Source ↗
! Grade B · 75/100 · ReviewSecurity assessment
✓No compromise signals44capabilities surfaced1known CVE5of 20 OWASP controls clear
Suspicious network referencesBroad capability surfaceSuspicious network referencesSuspicious network references
scanned 19h ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

Ollama

Ollama makes running open-weight LLMs locally as simple as ollama run llama3. It ships a cross-platform daemon with a fully OpenAI-compatible REST API, so any agent or tool that speaks to OpenAI can point to localhost:11434 and run on-device models with zero cloud dependency.

Key Features

  • One-command setup — curl -fsSL https://ollama.com/install.sh | sh on Linux/macOS
  • Model library — 100+ curated models: Llama 3, Mistral, Gemma 3, Phi-4, Qwen, DeepSeek, and multimodal models
  • OpenAI-compatible API — drop-in replacement for openai SDK clients by changing one base URL
  • GPU acceleration — NVIDIA CUDA, AMD ROCm, Apple Metal — automatic detection
  • Modelfile — parameterize, layer adapters, and customize system prompts in a Dockerfile-like format
  • Streaming — token-by-token streaming responses

Quick Start

# Install and run a model
ollama run llama3.2

# Use via OpenAI-compatible API
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "llama3.2", "messages": [{"role": "user", "content": "Hello!"}]}'

Install via ai-supply

npx ai-supply add ollama-local-model-runtime

Curated mirror of the open-source Ollama project (MIT). Install upstream from the repository.

Rating rank
#1
of 35 in Agentic capability
Install rank
#7
of 35 in Agentic capability
Security score
75/100 · B
review
Security rank
#23
of 35 in Agentic capability
Installs
296k
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 19h ago
✓ no compromise signals45 risk-surface · 10/20 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 (6)
ChatGPTOpenClawOpenCodeCodexDroidPi
⚑ filesystem⚑ network⚑ secrets
egress → discord.com, developer.download.nvidia.com, packages.nvidia.com, download.amd.com, sdk.lunarg.com, go.microsoft.com, azure.archive.ubuntu.com, azure.ports.ubuntu.com +32
auth: api_keygithub.comdiscord.comdeveloper.download.nvidia.compackages.nvidia.comdownload.amd.comsdk.lunarg.comgo.microsoft.comazure.archive.ubuntu.com

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 — 56 npm dependencies declared · ollama-ollama-64ee2f9/app/ui/app/package.jsonrisk surface
•Vulnerable dependencies — 171 known vulnerabilities in: @babel/core@7.27.4, @eslint/plugin-kit@0.3.3, @vitest/browser@3.2.4, ajv@6.12.6, brace-expansion@1.1.12, brace-expansion@2.0.2, diff@7.0.0, dompurify@3.3.0 (CWE-1395)known CVE · -25 pts
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected · ollama-ollama-64ee2f9/agent/compactor.go (CWE-77)expected
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — destructive rm -rf / · ollama-ollama-64ee2f9/Dockerfile (CWE-78)expected
•Suspicious code patterns — pipe-to-shell install · ollama-ollama-64ee2f9/README.md (CWE-494)expected
•Suspicious code patterns — dynamic code execution · ollama-ollama-64ee2f9/app/ui/app/src/components/ErrorMessage.tsx (CWE-95)expected
•Suspicious code patterns — destructive rm -rf /; pipe-to-shell install · ollama-ollama-64ee2f9/docs/linux.mdx (CWE-78)expected
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · ollama-ollama-64ee2f9/.github/ISSUE_TEMPLATE/10_bug_report.ymlexpected
•External endpoints declared — 2 distinct host(s) · ollama-ollama-64ee2f9/.github/ISSUE_TEMPLATE/config.ymlexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · ollama-ollama-64ee2f9/.github/workflows/release.yaml (CWE-272)risk surface
•External endpoints declared — 8 distinct host(s) · ollama-ollama-64ee2f9/.github/workflows/release.yamlexpected
•External endpoints declared — 7 distinct host(s) · ollama-ollama-64ee2f9/.github/workflows/test-llamacpp-update.yamlexpected
•External endpoints declared — 6 distinct host(s) · ollama-ollama-64ee2f9/.github/workflows/test.yamlexpected
•External endpoints declared — 48 distinct host(s) · ollama-ollama-64ee2f9/README.mdexpected
•Egress to a private/loopback host — 127.0.0.1 · ollama-ollama-64ee2f9/agent/session_test.go (CWE-918)expected
•External endpoints declared — 4 distinct host(s) · ollama-ollama-64ee2f9/api/client_test.goexpected
•External endpoints declared — 5 distinct host(s) · ollama-ollama-64ee2f9/app/README.mdexpected
•External endpoints declared — 10 distinct host(s) · ollama-ollama-64ee2f9/app/ui/app/package-lock.jsonexpected
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege · ollama-ollama-64ee2f9/cmd/interactive.go (CWE-272)risk surface
•Egress to a private/loopback host — 127.0.0.1, 0.0.0.0 · ollama-ollama-64ee2f9/cmd/launch/codex_app_test.go (CWE-918)expected
•External endpoints declared — 3 distinct host(s) · ollama-ollama-64ee2f9/cmd/launch/kimi_test.goexpected
•Egress to a private/loopback host — 0.0.0.0, 127.0.0.1 · ollama-ollama-64ee2f9/cmd/launch/omp_test.go (CWE-918)expected
•Egress to a private/loopback host — 10.0.0.20 · ollama-ollama-64ee2f9/cmd/launch/qwen_test.go (CWE-918)expected
•External endpoints declared — 13 distinct host(s) · ollama-ollama-64ee2f9/cmd/launch/registry.goexpected
•Egress to a private/loopback host — 127.0.0.1, [::1], [::], 192.168.1.5, 0.0.0.0, 10.0.0.1, 172.16.0.1, 192.168.0.1 · ollama-ollama-64ee2f9/envconfig/config_test.go (CWE-918)expected
•External endpoints declared — 16 distinct host(s) · ollama-ollama-64ee2f9/envconfig/config_test.goexpected
⚠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 · ollama-ollama-64ee2f9/cmd/cmd_test.go (CWE-200)risk surface
•Low-confidence secret match — 1 possible: generic-api-key · ollama-ollama-64ee2f9/model/parsers/glm46.go (CWE-798)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 · ollama-ollama-64ee2f9/app/ui/app/src/util/jsonl-parsing.ts (CWE-835)risk surface
⚠LLM02Sensitive Information Disclosurelow
Secrets, credentials or PII shipped inside the artifact.
•Low-confidence secret match — 1 possible: generic-api-key · ollama-ollama-64ee2f9/model/parsers/glm46.go (CWE-798)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓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 — 56 npm dependencies declared · ollama-ollama-64ee2f9/app/ui/app/package.jsonrisk surface
•Vulnerable dependencies — 171 known vulnerabilities in: @babel/core@7.27.4, @eslint/plugin-kit@0.3.3, @vitest/browser@3.2.4, ajv@6.12.6, brace-expansion@1.1.12, brace-expansion@2.0.2, diff@7.0.0, dompurify@3.3.0 (CWE-1395)known CVE · -25 pts
⚠ML02Data Poisoninghigh
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
•Prompt-injection phrasing — instruction-subversion language detected · ollama-ollama-64ee2f9/agent/compactor.go (CWE-77)expected
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — destructive rm -rf / · ollama-ollama-64ee2f9/Dockerfile (CWE-78)expected
•Suspicious code patterns — pipe-to-shell install · ollama-ollama-64ee2f9/README.md (CWE-494)expected
•Suspicious code patterns — dynamic code execution · ollama-ollama-64ee2f9/app/ui/app/src/components/ErrorMessage.tsx (CWE-95)expected
•Suspicious code patterns — destructive rm -rf /; pipe-to-shell install · ollama-ollama-64ee2f9/docs/linux.mdx (CWE-78)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.
✓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 (45) · hygiene / uncategorized
•Unrecognized file type — '.dockerignore' is not on the allowlist · ollama-ollama-64ee2f9/.dockerignorerisk surface
•Unrecognized file type — '.gitattributes' is not on the allowlist · ollama-ollama-64ee2f9/.gitattributesrisk surface
•Suspicious network references — suspicious TLD (19 URLs) · ollama-ollama-64ee2f9/.github/workflows/release.yamlrisk surface
•Suspicious network references — suspicious TLD (11 URLs) · ollama-ollama-64ee2f9/.github/workflows/test-llamacpp-update.yamlrisk surface
•Suspicious network references — suspicious TLD (9 URLs) · ollama-ollama-64ee2f9/.github/workflows/test.yamlrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · ollama-ollama-64ee2f9/.gitignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · ollama-ollama-64ee2f9/Dockerfilerisk surface
•Suspicious network references — suspicious TLD (17 URLs) · ollama-ollama-64ee2f9/Dockerfilerisk surface
•Suspicious network references — raw IP URL (1 URLs) · ollama-ollama-64ee2f9/agent/session_test.gorisk surface
•Suspicious network references — raw IP URL (24 URLs) · ollama-ollama-64ee2f9/api/client_test.gorisk surface
•Suspicious network references — raw IP URL (6 URLs) · ollama-ollama-64ee2f9/app/README.mdrisk surface
•Unrecognized file type — '.h' is not on the allowlist · ollama-ollama-64ee2f9/app/cmd/app/AppDelegate.hrisk surface
•Suspicious network references — raw IP URL (3 URLs) · ollama-ollama-64ee2f9/app/cmd/app/app.gorisk surface
•Unrecognized file type — '.m' is not on the allowlist · ollama-ollama-64ee2f9/app/cmd/app/app_darwin.mrisk surface
•Suspicious network references — raw IP URL (2 URLs) · ollama-ollama-64ee2f9/app/cmd/app/webview.gorisk surface
•Unrecognized file type — '.plist' is not on the allowlist · ollama-ollama-64ee2f9/app/cmd/squirrel/Info.plistrisk surface
•Unrecognized file type — '.iss' is not on the allowlist · ollama-ollama-64ee2f9/app/ollama.issrisk surface
•Unrecognized file type — '.rc' is not on the allowlist · ollama-ollama-64ee2f9/app/ollama.rcrisk surface
•Unrecognized file type — '.prettierignore' is not on the allowlist · ollama-ollama-64ee2f9/app/ui/app/.prettierignorerisk surface
•Unrecognized file type — '.prettierrc' is not on the allowlist · ollama-ollama-64ee2f9/app/ui/app/.prettierrcrisk surface
•Unrecognized file type — '.c' is not on the allowlist · ollama-ollama-64ee2f9/app/webview/glue.crisk surface
•Unrecognized file type — '.cc' is not on the allowlist · ollama-ollama-64ee2f9/app/webview/webview.ccrisk surface
•Unrecognized file type — '.cmake' is not on the allowlist · ollama-ollama-64ee2f9/cmake/local.cmakerisk surface
•Suspicious network references — raw IP URL (11 URLs) · ollama-ollama-64ee2f9/cmd/launch/cline_test.gorisk surface
•Suspicious network references — raw IP URL (35 URLs) · ollama-ollama-64ee2f9/cmd/launch/codex_app_test.gorisk surface
•Suspicious network references — raw IP URL (7 URLs) · ollama-ollama-64ee2f9/cmd/launch/codex_test.gorisk surface
•Suspicious network references — raw IP URL (19 URLs) · ollama-ollama-64ee2f9/cmd/launch/hermes_test.gorisk surface
•Suspicious network references — raw IP URL (10 URLs) · ollama-ollama-64ee2f9/cmd/launch/omp_test.gorisk surface
•Suspicious network references — raw IP URL (5 URLs) · ollama-ollama-64ee2f9/cmd/launch/openclaw.gorisk surface
•Suspicious network references — raw IP URL (4 URLs) · ollama-ollama-64ee2f9/cmd/launch/qwen_test.gorisk surface
•Unrecognized file type — '.proto' is not on the allowlist · ollama-ollama-64ee2f9/convert/sentencepiece_model.protorisk surface
•Unrecognized file type — '.mdx' is not on the allowlist · ollama-ollama-64ee2f9/docs/api/anthropic-compatibility.mdxrisk surface
•Suspicious network references — raw IP URL (99 URLs) · ollama-ollama-64ee2f9/envconfig/config_test.gorisk surface
•Unrecognized file type — '.mod' is not on the allowlist · ollama-ollama-64ee2f9/go.modrisk surface
•Unrecognized file type — '.sum' is not on the allowlist · ollama-ollama-64ee2f9/go.sumrisk surface
•Unrecognized file type — '.patch' is not on the allowlist · ollama-ollama-64ee2f9/llama/compat/001-llama-cpp-hooks.patchrisk surface
•Unrecognized file type — '.cpp' is not on the allowlist · ollama-ollama-64ee2f9/llama/compat/llama-ollama-compat-util.cpprisk surface
•Unrecognized file type — '.cu' is not on the allowlist · ollama-ollama-64ee2f9/ml/backend/ggml/ggml/src/ggml-cuda/template-instances/fattn-tile-instance-dkq512-dv512.curisk surface
•Unrecognized file type — '.jinja2' is not on the allowlist · ollama-ollama-64ee2f9/model/renderers/testdata/gemma4_31b_chat_template.jinja2risk surface
•Unrecognized file type — '.this-is-the-create-dmg-repo' is not on the allowlist · ollama-ollama-64ee2f9/scripts/.this-is-the-create-dmg-reporisk surface
•Disallowed file type — '.ps1' executables are not permitted · ollama-ollama-64ee2f9/scripts/build_windows.ps1 (CWE-434)risk surface
•Unrecognized file type — '.example' is not on the allowlist · ollama-ollama-64ee2f9/scripts/buildkitd.toml.examplerisk surface
•Unrecognized file type — '.applescript' is not on the allowlist · ollama-ollama-64ee2f9/scripts/support/template.applescriptrisk surface
•Unrecognized file type — '.gotmpl' is not on the allowlist · ollama-ollama-64ee2f9/template/alfred.gotmplrisk surface
•Unrecognized file type — '.jsonl' is not on the allowlist · ollama-ollama-64ee2f9/template/testdata/templates.jsonlrisk surface
✔ verified source · pinned ollama-ollama-64ee2f9 · changed since last scan · +egress packages.nvidia.com
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/ollama-local-model-runtime/check). Click a policy:

Consume Ollama 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/ollama-local-model-runtime

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

# CLI
npx ai-supply add ollama-local-model-runtime

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/ollama-local-model-runtime/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "ollama-local-model-runtime" })
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