SkillTotal

Is @earendil-works/pi-ai safe?

No malicious indicators - review capabilities before installing
Notable — review in context (capabilities are not malware):
  • Node.js network egress
  • Delegated authentication (OAuth 2.0 / OIDC)

@earendil-works/pi-ai is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 2 risky constructs are reported for review. It can: delegated authentication and network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

@earendil-works/pi-ai 0.99.1

npm_package · npm:@earendil-works/pi-ai
LOW
0
/ 100 risk score
Snapshot · scanned Sep 29, 2026 · @earendil-works/pi-ai@0.99.1 · 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 @earendil-works/pi-ai's authors. Report a false positive.

Capabilities — what this component can do (not a risk score):
delegated authenticationnetwork 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
Delegated authentication
Tool Execution Context / User Delegated Credentials

Findings (2)

MEDIUMNode.js network egressST-NET-NODE

The component makes outbound network requests.

* passthrough (`env.AI.fetch()`), which serves the gateway's provider passthrough at
* The only thing this module adds over calling `env.AI.fetch()` yourself is a type: `Ai#fetch`
* passthrough (`env.AI.fetch()`), which serves the gateway's provider passthrough at
* The only thing this module adds over calling `env.AI.fetch()` yourself is a type: `Ai#fetch`
throw new TypeError("createAiBindingFetch: the AI binding does not expose fetch()");
const response = await fetch(url, {
import { createServer } from "node:http";
const response = await fetch(url, {
const response = await fetch(url, init);
const response = await fetch(`${oauthHost}/api/oauth/device_authorization`, {
const response = await fetch(`${oauthHost}/api/oauth/token`, {
response = await fetch(`${oauthHost}/api/oauth/token`, {
const response = await fetch(DEVICE_AUTHORIZATION_URL, {
const response = await fetch(DEVICE_TOKEN_URL, {
const response = await fetch(API_KEY_MINT_URL, {
import { createServer } from "node:http";
const response = await fetch(TOKEN_URL, {
return await fetch(input, init);
response = await fetch(TOKEN_URL, {
response = await fetch(TOKEN_URL, {
const response = await fetch(new URL("/v1/oauth", gateway), {
response = await fetch(new URL("/v1/oauth/token", gateway), {
response = await fetch(new URL("/v1/oauth/device", gateway), {
response = await fetch(url, {
const response = await fetch(new URL("/v1/config", gateway), { headers, signal });

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.

LOWDelegated authentication (OAuth 2.0 / OIDC)ST-AUTH-DELEGATED

An OAuth 2.0 / OpenID Connect delegated-authentication flow was detected (authorization-code / refresh-token / token-exchange grant, an OIDC authorize/discovery endpoint or id_token, or a delegation library). Tools authenticate with the end user's delegated, scoped credentials rather than a long-lived embedded service credential. (15 occurrence(s) shown as evidence).

const AUTHORIZE_URL = "https://claude.ai/oauth/authorize";
grant_type: "authorization_code",
grant_type: "refresh_token",
grant_type: "refresh_token",
* (auth.meta.com answers grant_type=refresh_token with 404 and issues no
* (auth.meta.com answers grant_type=refresh_token with 404 and issues no
grant_type: "authorization_code",
if (typeof token.id_token !== "string" || token.id_token.trim().length === 0) {
const AUTHORIZE_URL = `${AUTH_BASE_URL}/oauth/authorize`;
grant_type: "authorization_code",
grant_type: "authorization_code",
grant_type: "refresh_token",
grant_type: "refresh_token",

Fix: Delegated auth is a lower-blast-radius execution context than an embedded static credential. Confirm the requested scopes are minimal and that tokens are never logged or forwarded 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 →