registry / autopilot-ai / 3.1.1
autopilot-ai@3.1.1
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 6d ago · by lpm-firewall-aiThe source ties the flagged gateway to an explicitly named Vercel provider and resolves endpoints by selected provider. The package declares no install hook beyond a build-only prepublish hook, and the reviewed dynamic execution is part of isolated code mode.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
Provider requests occur when the selected provider is used; code-mode and tool execution are part of agent workflows.
Impact
No malicious credential redirection, install-time collection, or concealed remote-code execution was identified.
Mechanism
Provider-specific configuration selects API endpoints, code mode runs in an isolated VM, and tool requests use permission handling.
AI rationale
The source ties the flagged gateway to an explicitly named Vercel provider and resolves endpoints by selected provider. The package declares no install hook beyond a build-only prepublish hook, and the reviewed dynamic execution is part of isolated code mode.
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 hook is prepublishOnly, which runs the package build; no install hook is declared.
- The flagged ai-gateway.vercel.sh endpoint belongs to the named Vercel AI Gateway provider and uses its own AI_GATEWAY_API_KEY.
- Provider URLs are resolved from the selected provider preset or that provider's configuration, rather than redirecting all credentials to one fixed host.
- The eval calls are part of an isolated-vm code-mode sandbox that bridges declared tools and executes supplied code.
- Tool requests pass through the package's permission handling.
Evidence against
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
15 flaggeddist/index.jsView file
1333const iat = Math.floor(now2 / 1e3);
L1334: const payload = enc({ iss: sa.client_email, scope: SCOPE, aud: sa.token_uri ?? "https://oauth2.googleapis.com/token", iat, exp: iat + 3600 });
L1335: const signature = createSign("RSA-SHA256").update(`${header}.${payload}`).sign(sa.private_key).toString("base64url");
...
L1340: const tokenUrl = creds.type === "service_account" ? creds.token_uri ?? "https://oauth2.googleapis.com/token" : "https://oauth2.googleapis.com/token";
L1341: const body = creds.type === "service_account" ? new URLSearchParams({ grant_type: "urn:ietf:params:oauth:grant-type:jwt-bearer", assertion: signJwt(creds, now2) }) : new URLSearchP...
L1342: const res = await fetchImpl2(tokenUrl, { method: "POST", headers: { "Content-Type": "application/x-www-form-urlencoded" },
Critical
Command Output Exfiltration
Source executes local commands and sends command output to an external endpoint.
dist/index.jsView on unpkg · L133339function home(env) {
L40: return env.HOME || homedir();
L41: }
...
L50: }
L51: function configDir(env = process.env) {
L52: return join(configHome(env), APP_DIR_NAME);
...
L310: stream.once("error", () => resolve25());
L311: stream.end();
L312: });
...
L461: function setFetchForTesting(f) {
L462: fetchImpl = f ?? ((url, init) => fetch(url, init));
L463: }
Critical
Dns Exfiltration
Source appears to send environment or credential material through DNS lookups.
dist/index.jsView on unpkg · L39Findings
6 Critical8 High4 Medium6 Low
CriticalHardcoded Runtime Data Exfiltrationdist/sdk/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/index.js
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@3.1.1.
See all versions of autopilot-ai for other recorded verdicts.
- Review the evidence and your use of autopilot-ai@3.1.1 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.