registry / autopilot-ai
autopilot-ai
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.
This report shows the evidence for autopilot-ai@3.9.0. 0 of 40 known versions are blocked or flagged. See all versions.
AI Security Review
scanned 5h ago · by lpm-firewall-aiThe reviewed entry points and runtime paths show provider requests, opt-in OTLP export, and isolated code-mode execution consistent with the package’s purpose. The manifest has no install hook; its prepublishOnly script runs the build.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
The CLI runs when invoked; model requests, tool use, and telemetry export require their respective runtime configuration or user activity.
Impact
No unauthorized credential forwarding, install-time data collection, or unrelated remote code execution was identified.
Mechanism
Provider credentials go to the configured provider endpoint. OTLP export requires an explicitly configured endpoint. Code mode runs transpiled code in an isolated VM with a timeout.
AI rationale
The reviewed entry points and runtime paths show provider requests, opt-in OTLP export, and isolated code-mode execution consistent with the package’s purpose. The manifest has no install hook; its prepublishOnly script runs the build.
Network endpoints3
api.openai.com/v1api.anthropic.com/v1free.directionallylocal.com
Decision evidence
public snapshotAI called this Clean at 91.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest’s prepublishOnly script runs the build; the package exposes a CLI and SDK.
- Provider configuration pairs OpenAI’s API endpoint with OPENAI_API_KEY, and the README documents provider/key choices.
- OTLP export is disabled unless OTEL_ENDPOINT is configured.
- The dynamic code path transpiles supplied code and runs it in an isolated VM with a timeout, consistent with the coding-agent feature.
Evidence against
Behavioral surface
ChildProcessCryptoDynamicRequireEnvironmentVarsEvalFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
16 flaggeddist/index.jsView file
1435const iat = Math.floor(now2 / 1e3);
L1436: const payload = enc({ iss: sa.client_email, scope: SCOPE, aud: sa.token_uri ?? "https://oauth2.googleapis.com/token", iat, exp: iat + 3600 });
L1437: const signature2 = createSign("RSA-SHA256").update(`${header}.${payload}`).sign(sa.private_key).toString("base64url");
...
L1442: const tokenUrl = creds.type === "service_account" ? creds.token_uri ?? "https://oauth2.googleapis.com/token" : "https://oauth2.googleapis.com/token";
L1443: const body = creds.type === "service_account" ? new URLSearchParams({ grant_type: "urn:ietf:params:oauth:grant-type:jwt-bearer", assertion: signJwt(creds, now2) }) : new URLSearchP...
L1444: const res = await fetchImpl3(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 · L143536} from "fs";
L37: import { execFileSync } from "child_process";
L38: import { homedir, userInfo } from "os";
...
L40: function home(env) {
L41: return guardTestPath(env.HOME || homedir());
L42: }
...
L51: }
L52: function isAutopilotTestRun(env = process.env) {
L53: if (env.AUTOPILOT_TEST_ROOT) return true;
...
L376: stream.once("error", () => resolve33());
L377: stream.end();
L378: });
Critical
Dns Exfiltration
Source appears to send environment or credential material through DNS lookups.
dist/index.jsView on unpkg · L36Findings
6 Critical9 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/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@3.9.0.
The versions list below shows the verdict for each recorded version.
- Review the evidence and your use of autopilot-ai@3.9.0 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.