@roarkanalytics/sdk-mcp@4.8.0
The official MCP Server for the Roark API
AI Security Review
scanned 24d ago · by lpm-firewall-aiThis is a concrete conditional credential-forwarding capability rather than confirmed malware. The absence of lifecycle hooks reduces install-time risk, but the unrestricted endpoint override prevents a clean verdict.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review
Trigger
Invoking the enabled execute tool while it uses the default remote mode.
Impact
A configured untrusted endpoint could receive an existing Roark credential.
Mechanism
The handler reads the bearer token, merges it into client environment values, and POSTs those values to the configured code-mode endpoint.
AI rationale
This is a concrete conditional credential-forwarding capability rather than confirmed malware. The absence of lifecycle hooks reduces install-time risk, but the unrestricted endpoint override prevents a clean verdict.
Evidence
code-tool.mjsserver.mjs
Network endpoints1
api.stainless.com/api/ai/code-tool
Decision evidence
public snapshotAI called this Suspicious at 93.0% confidence as Dangerous Capability with low false-positive risk.
Evidence for warning
- The execute tool is enabled by default and defaults to the remote stainless-sandbox mode.
- Remote execution obtains the Roark bearer token from the environment or initialized client.
- The remote handler posts merged client environment values, including that token, to an endpoint selected from CODE_MODE_ENDPOINT_URL or a Stainless default.
- The package has no npm preinstall, install, or postinstall script.
Evidence against
- The default endpoint is a named Stainless service, but the endpoint override has no destination allowlist.
- No install-time execution or unrelated destructive behavior was found in the inspected paths.
Behavioral surface
ChildProcessDynamicRequireEnvironmentVarsFilesystemNetwork
HighEntropyStringsUrlStrings
Source & flagged code
11 flagged · loading sourceinstructions.jsView file
•matchType = normalized_sha256
matchedPackage = plumery-mcp@3.9.0
matchedPath = instructions.js
matchedIdentity = npm:cGx1bWVyeS1tY3A:3.9.0
similarity = 1.000
summary = normalized source hash matched finalized malicious source
High
Known Malware Source Similarity
Source file is highly similar to a previously finalized malicious package; route for source-aware review.
instructions.jsView on unpkg7exports.getInstructions = getInstructions;
L8: const promises_1 = __importDefault(require("fs/promises"));
L9: const logger_1 = require("./logger.js");
Medium
Dynamic Require
Package source references dynamic require/import behavior.
instructions.jsView on unpkg · L7code-tool.jsView file
52Source sends the broad process environment to a literal external destination.
L52: interfaceType: 'PHONE',
L53: recordingUrl: 'https://example.com',
L54: startedAt: 'startedAt',
...
L155: },
L156: body: JSON.stringify({
L157: project_name: 'roark-analytics',
...
L166: }
L167: throw new Error(`${res.status}: ${res.statusText} error when trying to contact Code Tool server. Details: ${await res.text()}`);
L168: }
...
L214: // Check if deno is in PATH
L215: const { execSync, spawn } = await Promise.resolve().then(() => __importStar(require('node:child_process')));
L216: try {
Findings
2 Critical7 High5 Medium4 Low
CriticalHardcoded Runtime Data Exfiltrationcode-tool.js
CriticalManifest Confusionpackage.json
HighSemantic Analysis Limitedcode-tool.js#virtual:normalized:round1
HighKnown Malware Source Similaritycode-tool.js
HighKnown Malware Source Similaritycode-tool.mjs
HighKnown Malware Source Similaritysrc/code-tool.ts
HighKnown Malware Source Similaritycode-tool-worker.js
HighKnown Malware Source Similarityinstructions.js
HighKnown Malware Source Similaritylocal-docs-search.js
MediumDynamic Requireinstructions.js
MediumNetwork
MediumEnvironment Vars
Affected versions and remediation
This report applies to @roarkanalytics/sdk-mcp@4.8.0.
See all versions of @roarkanalytics/sdk-mcp for other recorded verdicts.
- Review the evidence and your use of @roarkanalytics/sdk-mcp@4.8.0 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.