registry / autopilot-ai / 2.9.0
autopilot-ai@2.9.0
autopilot (formerly kimiflare): a terminal coding agent for any model with your own key: OpenRouter, Anthropic, OpenAI, Gemini, Bedrock, Vertex, Ollama and more. Per-turn cost, web search, GitHub, headless browser, LSP, MCP, local memory.
AI Security Review
scanned 7d ago · by lpm-firewall-aiThe manifest has no install-time hook, and the flagged gateway is a named provider with its own key configuration. The dynamic execution found is for agent-generated code inside a resource-bounded isolated VM; the reviewed evidence did not establish unrelated credential or command-output exfiltration.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
The user runs the CLI and selects a provider or submits a coding task.
Impact
No malicious impact was established from the inspected source.
Mechanism
The agent connects to its configured model provider and runs generated code in an isolated VM with bounded memory and execution time.
AI rationale
The manifest has no install-time hook, and the flagged gateway is a named provider with its own key configuration. The dynamic execution found is for agent-generated code inside a resource-bounded isolated VM; the reviewed evidence did not establish unrelated credential or command-output exfiltration.
Network endpoints1
ai-gateway.vercel.sh
Decision evidence
public snapshotAI called this Clean at 93.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The only lifecycle script is prepublishOnly, which runs the build; there is no install hook.
- The autopilot executable imports the package’s CLI entry point.
- The Vercel AI Gateway is a named provider with its own API key and dashboard.
- Provider selection comes from an environment setting or saved configuration.
- Generated JavaScript is run in an isolated VM with a memory limit and execution timeout.
Evidence against
- The package is described and wired as a terminal coding agent, so model access and tool execution serve its stated purpose.
- No source evidence confirmed credential theft, DNS exfiltration, or unrelated command-output transmission.
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
15 flaggeddist/index.jsView file
41Source sends the broad process environment to a literal external destination.
L41: function defaultLogDir() {
L42: const xdg = process.env.XDG_CONFIG_HOME || join(homedir(), ".config");
L43: return join(xdg, "kimiflare", "logs");
...
L58: if (currentStream) {
L59: currentStream.end();
L60: currentStream = null;
...
L188: function setFetchForTesting(f) {
L189: fetchImpl = f ?? ((url, init) => fetch(url, init));
L190: }
...
L989: import { createSign } from "crypto";
L990: import { execFile } from "child_process";
L991: import { readFile } from "fs/promises";
Critical
Hardcoded Runtime Data Exfiltration
Source sends credentials or rich application records to a package-controlled external receiver enabled by default.
dist/index.jsView on unpkg · L411055const iat = Math.floor(now2 / 1e3);
L1056: const payload = enc({ iss: sa.client_email, scope: SCOPE, aud: sa.token_uri ?? "https://oauth2.googleapis.com/token", iat, exp: iat + 3600 });
L1057: const signature = createSign("RSA-SHA256").update(`${header}.${payload}`).sign(sa.private_key).toString("base64url");
...
L1062: const tokenUrl = creds.type === "service_account" ? creds.token_uri ?? "https://oauth2.googleapis.com/token" : "https://oauth2.googleapis.com/token";
L1063: const body = creds.type === "service_account" ? new URLSearchParams({ grant_type: "urn:ietf:params:oauth:grant-type:jwt-bearer", assertion: signJwt(creds, now2) }) : new URLSearchP...
L1064: const res = await fetchImpl2(tokenUrl, { method: "POST", headers: { "Content-Type": "application/x-www-form-urlencoded" },
Critical
Command Output Exfiltration
Findings
6 Critical8 High4 Medium6 Low
CriticalHardcoded Runtime Data Exfiltrationdist/index.js
CriticalCommand Output Exfiltrationdist/index.js
CriticalDns Exfiltrationdist/index.js
CriticalRemote Response Code Executiondist/index.js
CriticalTrigger Reachable Dangerous Capabilitydist/index.js
CriticalPrevious Version Dangerous Deltadist/sdk/index.d.ts
HighChild Processdist/index.js
HighShelldist/index.js
HighEval
HighSame File Env Network Executiondist/index.js
HighCredential Redirect Persistencedist/index.js
HighRemote Agent Bridgedist/index.js
Affected versions and remediation
This report applies to autopilot-ai@2.9.0.
See all versions of autopilot-ai for other recorded verdicts.
- Review the evidence and your use of autopilot-ai@2.9.0 before allowing it. Restrict the permissions described in this report.
- Choose an independently verified alternative or release. This report does not establish that other versions are safe.
Evidence last updated: .
Think this verdict is wrong? Dispute it on GitHub or read how reports are produced.