SkillTotal

Is ollama/ollama safe?

No malicious indicators - review capabilities before installing
Notable — review in context (capabilities are not malware):
  • Node.js network egress

repo is an AI go_project analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 1 risky construct are reported for review. It can: network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

repo

go_project · https://github.com/ollama/ollama
LOW
0
/ 100 risk score
Snapshot · scanned Sep 30, 2026 · repo@1abe35e · engine 0.53.0 / ruleset 60

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of ollama/ollama'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.

app/ui/app/src/api.ts:51-51 
const response = await fetch(`${API_BASE}/api/v1/integrations`);
app/ui/app/src/api.ts:63-63 
const response = await fetch(
app/ui/app/src/api.ts:111-111 
const response = await fetch(`${API_BASE}/api/me`, {
app/ui/app/src/api.ts:136-136 
const response = await fetch(`${API_BASE}/api/me`, {
app/ui/app/src/api.ts:156-156 
const response = await fetch(`${API_BASE}/api/signout`, {
app/ui/app/src/api.ts:169-169 
const response = await fetch(`${API_BASE}/api/v1/chats`);
app/ui/app/src/api.ts:175-175 
const response = await fetch(`${API_BASE}/api/v1/chat/${chatId}`);
app/ui/app/src/api.ts:250-250 
? fetch(`${API_BASE}/api/v1/models/cloud`)
app/ui/app/src/api.ts:364-364 
const response = await fetch(`${API_BASE}/api/v1/chat/${chatId}`, {
app/ui/app/src/api.ts:405-405 
const response = await fetch(`${API_BASE}/api/v1/settings`);
app/ui/app/src/api.ts:418-418 
const response = await fetch(`${API_BASE}/api/v1/settings`, {
app/ui/app/src/api.ts:438-438 
const response = await fetch(`${API_BASE}/api/v1/cloud`, {
app/ui/app/src/api.ts:458-458 
const response = await fetch(`${API_BASE}/api/v1/chat/${chatId}/rename`, {
app/ui/app/src/api.ts:472-472 
const response = await fetch(`${API_BASE}/api/v1/chat/${chatId}`, {
app/ui/app/src/api.ts:486-486 
const response = await fetch(`${API_BASE}/api/v1/model/upstream`, {
app/ui/app/src/api.ts:527-527 
const response = await fetch(`${API_BASE}/api/v1/models/pull`, {
app/ui/app/src/api.ts:566-566 
const response = await fetch(
app/ui/app/src/api.ts:579-579 
const response = await fetch(`${API_BASE}/api/v1/inference-compute`);
app/ui/app/src/api.ts:593-593 
const response = await fetch(`${API_BASE}/api/version`, {
app/ui/app/src/api.ts:614-614 
const response = await fetch(`${API_BASE}/api/v1/cloud`);

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 →