@roarkanalytics/sdk-mcp@3.30.1
The official MCP Server for the Roark API
AI Security Review
scanned 1mo ago · by lpm-firewall-aiThe package has no install-time persistence or automatic execution, but its library default can disclose API credentials to a hard-coded third-party execution endpoint. This warrants a warning rather than a malware block because the behavior is tool-invoked and the normal CLI disables that remote path.
Static reason
High-risk behavior combination matched malicious policy.; source matched previously finalized malicious package; routed for review
Trigger
An MCP client invokes the execute tool through the library API with remote mode selected by default.
Impact
The remote service can receive the Roark API bearer token and supplied client environment values.
Mechanism
Remote code execution request carrying credential-bearing environment data.
AI rationale
The package has no install-time persistence or automatic execution, but its library default can disclose API credentials to a hard-coded third-party execution endpoint. This warrants a warning rather than a malware block because the behavior is tool-invoked and the normal CLI disables that remote path.
Evidence
code-tool.jsserver.jscode-tool-worker.js
Network endpoints1
api.stainless.com/api/ai/code-tool
Decision evidence
public snapshotAI called this Suspicious at 86.0% confidence as Dangerous Capability with medium false-positive risk.
Evidence for warning
- The remote execute path sends the Roark bearer token and supplied client environments to api.stainless.com.
- The library API enables the code tool and defaults it to the remote Stainless mode when options are absent.
- The code worker dynamically imports caller-supplied TypeScript.
Evidence against
- package.json has no install lifecycle hook or self-dependency.
- The normal CLI defaults to local execution and explicitly rejects the retired remote mode.
- The credential transfer occurs only when the execute tool is invoked; no import-time exfiltration was found.
Behavioral surface
ChildProcessDynamicRequireEnvironmentVarsFilesystemNetworkShell
HighEntropyStringsUrlStrings
Source & flagged code
11 flagged · loading sourceinstructions.jsView file
•matchType = normalized_sha256
matchedPackage = cas-parser-node-mcp@1.17.1
matchedPath = instructions.js
matchedIdentity = npm:Y2FzLXBhcnNlci1ub2RlLW1jcA:1.17.1
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@3.30.1.
See all versions of @roarkanalytics/sdk-mcp for other recorded verdicts.
- Review the evidence and your use of @roarkanalytics/sdk-mcp@3.30.1 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.