registry / @makerx/yoke / 0.8.1
@makerx/yoke@0.8.1
Lean, user-invoked Claude Code skills for MakerX AI-assisted delivery, plus the CLI they call.
AI Security Review
scanned 3d ago · by lpm-firewall-aiThe flagged process, network, and agent-configuration behaviors are used by the package’s CLI features and are triggered by explicit commands. Model credentials are sent to the configured provider endpoint, while skill files are written by `yoke sync`.
Static reason
One or more suspicious static signals were detected.
Trigger
The CLI runs when a user invokes a command; `sync`, review, and provider probes run through their respective commands.
Impact
Expected PR review, provider connectivity checks, and skill setup; no malicious collection or unrequested agent configuration change was identified.
Mechanism
Review commands use `gh` for PR operations and send minimal model probes to the configured provider URL with its API key. `sync` writes the package’s bundled Claude Code skills.
AI rationale
The flagged process, network, and agent-configuration behaviors are used by the package’s CLI features and are triggered by explicit commands. Model credentials are sent to the configured provider endpoint, while skill files are written by `yoke sync`.
Evidence
.claude/skills/<skill>/SKILL.md~/.claude/skills/<skill>/SKILL.md.github/workflows/review-pr.yml
Network endpoints2
github.comUser-configured model provider base URL
Decision evidence
public snapshotAI called this Clean at 98.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The manifest exposes `dist/cli.js` as a CLI and its `prepublishOnly` script only runs the build.
- Model probes use the configured provider base URL and send the provider API key with a minimal `ping` request.
- GitHub operations use the installed `gh` CLI as part of PR commands.
- Agent skill files are written only by the explicit `yoke sync` command, to the project or user `.claude/skills` directory.
Evidence against
- The scanner’s command execution and network signals correspond to the package’s CLI review and provider-probe features.
- The scanner’s agent configuration write signal corresponds to a user-invoked skill synchronization command.
Behavioral surface
ChildProcessEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
4 flaggeddist/cli.jsView file
285// src/features/pr/raise.ts
L286: import { execFileSync } from "child_process";
L287:
High
1793async function claudeSignedIn() {
L1794: const { ok, stdout } = await exec("claude", ["auth", "status", "--json"]);
L1795: if (!ok) return false;
...
L1804: try {
L1805: const response = await fetch(url, {
L1806: method: "POST",
L1807: headers: { "Content-Type": "application/json", ...headers },
L1808: body: JSON.stringify(body),
L1809: signal: AbortSignal.timeout(probeTimeout)
High
Command Output Exfiltration
Source combines command execution, command-output handling, and outbound requests; review data flow before blocking.
dist/cli.jsView on unpkg · L1793•Runtime or CLI code links a write operation to an explicit external AI-agent control path:
telling the user to commit and push the workflow file.
if \`yoke\` is not found, run \`npm i -g @makerx/yoke\` and retry.
`
};
var reviewskill = {
name: "review",
description: "adversarially review a pr with claude and codex, then combine their findings.",
disablemodelinvocation: true,
body: `
run \`yoke review $arguments\` in the foreground, not as a background task, with the longest timeout your shell tool allows, so the user sees each reviewer's progress as it streams; two reviewers and a synthesis pass take several minutes. then relay the findings it printed. do not add findings of your own or re-review the code. each reviewer's tool calls go to \`review.
Findings
5 High2 Medium5 Low
HighChild Processdist/cli.js
HighShell
HighCommand Output Exfiltrationdist/cli.js
HighExternal Ai Agent Control Surface Mutationdist/cli.js
HighTrigger Reachable Command Output Exfiltrationdist/cli.js
MediumNetwork
MediumEnvironment Vars
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
Affected versions and remediation
This report applies to @makerx/yoke@0.8.1.
See all versions of @makerx/yoke for other recorded verdicts.
- Review the evidence and your use of @makerx/yoke@0.8.1 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.