clavue-v1@1.15.4
Clavue v1: lightweight four-slot (main/light/plan/review) multi-model coding CLI on the execution-first engine — overlapped cross-family review, official Clavue cloud preset (api.clavue.com) alongside any Messages-compatible provider, learned context ceil
AI Security Review
scanned 13d ago · by lpm-firewall-aiSource inspection did not establish credential exfiltration or other concrete attack behavior. The inspected scanner-flagged primitives are consistent with the package’s CLI, provider client, and sandbox proxy.
Static reason
High-risk behavior combination matched malicious policy.
Trigger
A user invokes the package CLI or uses its provider and sandbox features.
Impact
No confirmed malicious effect or attack surface was established.
Mechanism
The inspected excerpts show CLI process support, HTTP CONNECT proxy setup, and provider-client authentication initialization; they do not establish unrelated credential forwarding or another malicious action.
AI rationale
Source inspection did not establish credential exfiltration or other concrete attack behavior. The inspected scanner-flagged primitives are consistent with the package’s CLI, provider client, and sandbox proxy.
Decision evidence
public snapshotAI called this Clean at 81.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- package.json exposes a CLI and lists build and start scripts, with no lifecycle hook shown in its scripts section.
- The flagged command execution is in a bundled CLI command module; the inspected excerpt shows its module wrapper.
- The sandbox runtime CLI imports spawn as part of its CLI implementation.
- The provider router initializes Anthropic authentication from the API key and auth token environment variables for its client.
- The flagged proxy code creates an HTTP server to handle CONNECT requests.
Evidence against
- The inspected credential handling initializes the Anthropic client; no unrelated credential recipient or send operation was established.
- The scanner hints identify network and process primitives, but the inspected excerpts show provider-client, CLI, and proxy components rather than a confirmed attack chain.
Behavioral surface
ChildProcessCryptoEnvironmentVarsFilesystemNetworkShell
Source & flagged code
11 flagged · loading sourcedist/mao-command.jsView file
4var __create=Object.create;var __defProp=Object.defineProperty;var __getOwnPropDesc=Object.getOwnPropertyDescriptor;var __getOwnPropNames=Object.getOwnPropertyNames;var __getProtoO...
L5: GFS4: `),console.error(m)},"debug"));fs6[gracefulQueue]||(queue=global[gracefulQueue]||[],publishQueue(fs6,queue),fs6.close=(function(fs$close){function close(fd,cb){return fs$clos...
L6: `,"utf8"),process4.platform!=="win32")try{fs.chmodSync(filePath,384)}catch{}}__name(defaultWriteJsonFile,"defaultWriteJsonFile");function defaultSafeReadFile(filePath){try{return f...
High
Child Process
Package source references child process execution.
dist/mao-command.jsView on unpkg · L4node_modules/@anthropic-ai/sandbox-runtime/dist/cli.jsView file
44.option('-s, --settings <path>', 'path to config file (default: ~/.srt-settings.json)')
L45: .option('-c <command>', 'run command string directly (like sh -c), no escaping applied')
L46: .option('--control-fd <fd>', 'read config updates from file descriptor (JSON lines protocol)', parseInt)
High
Shell
Package source references shell execution.
node_modules/@anthropic-ai/sandbox-runtime/dist/cli.jsView on unpkg · L44Findings
1 Critical6 High7 Medium5 Low
CriticalCredential Exfiltrationdist/provider-router.js
HighChild Processdist/mao-command.js
HighShellnode_modules/@anthropic-ai/sandbox-runtime/dist/cli.js
HighSame File Env Network Executiondist/provider-router.js
HighCommand Output Exfiltrationdist/provider-router.js
HighCloud Metadata Accessdist/provider-router.js
HighSemantic Analysis Limitednode_modules/@anthropic-ai/sandbox-runtime/dist/sandbox/http-proxy.js#virtual:normalized:round1
MediumNetwork
MediumEnvironment Vars
MediumShips Native Binarydist/vendor/ripgrep/x64-darwin/rg
MediumShips Build Helperinstall.sh
Medium
Affected versions and remediation
This report applies to clavue-v1@1.15.4.
See all versions of clavue-v1 for other recorded verdicts.
- Review the evidence and your use of clavue-v1@1.15.4 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.