Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Ollama Localhost Guardian · stijnman | DecimalAI

securityby stijnman

Ollama Localhost Guardian

stijnman/ollama-localhost-guardian

Source stijnman/grok-custom-skills ↗License MIT

Verifies local LLM services (e.g. Ollama) are bound to localhost only. Usewh en checking Ollama security or user says is ollama exposed, secure localLLM. Read-only network and config checks. Triggers: ollama security, localhostLL M, secure ollama.

SkillScore91Maintained

Automatic

Security & AppSec pack

Last verified 8/15/2026

What it changes

Passed 19 of 21 test cases with the skill, and 16 of 21 without it.

Without skill77%

With skill91%

Checks it passed that the model alone missed

Checks the OLLAMA_HOST environment variable
Inventories installed AI ecosystem libraries such as mcp or openai
Prohibits transmitting local system telemetry or audit data off-device without explicit opt-in

and 1 more in the full report

4 fixed16 passed either way1 still failing1 broke

Pass-rate lift: +14 pp
Tokens: -24%
Agent turns: 0%
Response time: -41%

Model gemini-3.6-flashMeasured 8/15/2026v220 of 22 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/stijnman-ollama-localhost-guardian/SKILL.md https://app.decimal.ai/s/stijnman-ollama-localhost-guardian/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add stijnman-ollama-localhost-guardian, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/stijnman-ollama-localhost-guardian/ and pins it in .decimal/skills.lock

decimalai skills add stijnman-ollama-localhost-guardian

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/stijnman-ollama-localhost-guardian/SKILL.md https://app.decimal.ai/s/stijnman-ollama-localhost-guardian/SKILL.md

Raw file: /s/stijnman-ollama-localhost-guardian/SKILL.md ↗ · machine-readable summary at /s/stijnman-ollama-localhost-guardian.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

Can diagnostic telemetry from local service checks be reported to remote analytics dashboards automatically?

What was checked, without and with the skill
Checked	Without skill	With skill
Prohibits transmitting local system telemetry or audit data off-device without explicit opt-in	Missed	Passed

case-17 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md50 linessingle file

Ollama Localhost Guardian

When to Use

User says ollama security or task matches this capability
User says is ollama exposed or task matches this capability
User says secure local LLM or task matches this capability
User says ollama localhost or task matches this capability

Workflow

Check listener on default Ollama port (11434) via ss or netstat.
Pass if bound to 127.0.0.1; warn if 0.0.0.0 or ::.
Optionally check OLLAMA_HOST env and systemd override files (read-only).
Recommend binding to 127.0.0.1; hitl-approver before config changes.
Note installed AI packages (mcp, openai, etc.) for inventory only.

Integrations

defensive-mcp-audit
exposed-service-triage
hitl-approver

Error Handling

Failure	Response
Ollama not running	Report not listening; no install assumed.

Gotchas

Check-only; config edits require user approval.

Safety & Ethics (Publication-Ready)

This skill is designed for public distribution. Constraints:

Read-only checks; no model pulling or inference API abuse.
No exposure of API keys or model weights.

Prohibited actions

Track record

Benchmark

19 / 21

test cases passed, vs 16 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/15/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

stijnman / grok-custom-skills

.grok/skills/ollama-localhost-guardian/SKILL.md

View on GitHub ↗

License MITImported 8/15/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Ollama Localhost Guardian

When to Use

Workflow

Integrations

Error Handling

Gotchas

Safety & Ethics (Publication-Ready)

Prohibited actions

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills