autopilot-ai@3.7.0
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 14h ago · by lpm-firewall-aiThe source reports provider-specific usage data to the provider's own service, but also includes an undisclosed hash derived from the Git origin. This warrants a telemetry warning; the reviewed code did not show credential or source-content exfiltration.
Static reason
High-risk behavior combination matched malicious policy.; previous stored version diff introduced dangerous source
Trigger
A session starts with the directionally-local provider.
Impact
The service can correlate usage with a repository; the inspected payload does not include the raw remote, prompts, code, or credentials.
Mechanism
The package hashes the Git origin URL, adds the hash to session events, and posts events to the provider's service.
AI rationale
The source reports provider-specific usage data to the provider's own service, but also includes an undisclosed hash derived from the Git origin. This warrants a telemetry warning; the reviewed code did not show credential or source-content exfiltration.
Evidence
dist/index.js
Network endpoints1
free.directionallylocal.com/v1/events
Decision evidence
public snapshotAI called this Suspicious at 84.0% confidence as Unknown with medium false-positive risk.
Evidence for warning
- Sessions using the directionally-local provider enable usage event reporting.
- The code hashes the Git origin URL and includes that hash in session events.
- Usage events are posted to the provider's own service; the built-in disclosure lists reported fields but omits the repository hash.
Evidence against
- The reporting is limited to sessions using the directionally-local provider.
- The inspected event payload contains usage and project-hash metadata, not prompts, code, raw Git remotes, or credentials.
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@3.7.0.
See all versions of autopilot-ai for other recorded verdicts.
- Review the evidence and your use of autopilot-ai@3.7.0 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.