registry / autopilot-ai / 3.6.0
autopilot-ai@3.6.0
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 19h ago · by lpm-firewall-aiThe flagged credential and command behaviors are consistent with a coding agent that sends requests to the selected model provider and runs shell commands after prompting for permission. The manifest has no install hook; its only lifecycle script builds the package before publishing.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
The user runs the CLI or SDK and configures a model provider; shell commands require a permission prompt.
Impact
No evidence found of automatic credential redirection, command-output exfiltration, or install-time data collection.
Mechanism
Provider credentials are associated with their configured service endpoints. The Vercel gateway is an explicitly named provider requiring its own key. Shell execution is described as permission-gated.
AI rationale
The flagged credential and command behaviors are consistent with a coding agent that sends requests to the selected model provider and runs shell commands after prompting for permission. The manifest has no install hook; its only lifecycle script builds the package before publishing.
Network endpoints2
api.anthropic.comai-gateway.vercel.sh
Decision evidence
public snapshotAI called this Clean at 88.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The only lifecycle script is prepublishOnly, which runs the package build.
- Anthropic credentials are configured for Anthropic’s official API endpoint.
- Vercel AI Gateway is a named provider preset with its own AI_GATEWAY_API_KEY.
- The shell tool description says it prompts the user for permission before executing commands.
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/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@3.6.0.
See all versions of autopilot-ai for other recorded verdicts.
- Review the evidence and your use of autopilot-ai@3.6.0 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.