SkillTotal

Is @openrouter/ai-sdk-provider safe?

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

@openrouter/ai-sdk-provider is an AI npm_package 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).

@openrouter/ai-sdk-provider 3.1.0

npm_package · npm:@openrouter/ai-sdk-provider
LOW
0
/ 100 risk score
Snapshot · scanned Sep 25, 2026 · @openrouter/ai-sdk-provider@3.1.0 · 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 @openrouter/ai-sdk-provider'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.

return ((input, init) => fetch(
const response = await fetch(currentUrl, perHopInit("manual"));
return await fetch(currentUrl, perHopInit("follow"));
const response = await fetch(url, {
return ((input, init) => fetch(
const response = await fetch(currentUrl, perHopInit("manual"));
return await fetch(currentUrl, perHopInit("follow"));
const response = await fetch(url, {

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 →