registry / code-i18n-agent / 0.1.9
code-i18n-agent@0.1.9
智能体：自动将代码项目国际化的扫描-分类-提取-翻译-替换-验证管线（不限于 ERP，适配 Vue/React/TS/JS/HTML）
AI Security Review
scanned 2d ago · by lpm-firewall-aiThe flagged credential flow uses a user-configured OpenAI-compatible endpoint and runs only as part of the CLI's LLM feature. The subprocess supports MCP tool calls, and no install-time attack or unrelated data flow was found.
Static reason
One or more suspicious static signals were detected.; previous stored version diff introduced dangerous source
Trigger
The user runs a CLI command or invokes an MCP tool; LLM requests require configured LLM credentials or an explicit LLM option.
Impact
No unauthorized data collection or unrelated account action was identified. The requested workflow can read or modify the user-selected project.
Mechanism
The MCP server starts the package's CLI helper for tool calls. When configured, the CLI sends messages and its configured API key to the OpenAI-compatible base URL.
AI rationale
The flagged credential flow uses a user-configured OpenAI-compatible endpoint and runs only as part of the CLI's LLM feature. The subprocess supports MCP tool calls, and no install-time attack or unrelated data flow was found.
Network endpoints1
api.openai.com/v1/chat/completions
Decision evidence
public snapshotAI called this Clean at 93.0% confidence as Benign with low false-positive risk.
Evidence for AI clean decision
- The package describes a code internationalization pipeline and exposes CLI and MCP entry points for that purpose.
- The CLI only loads LLM credentials when the user requests LLM use or the corresponding environment variable is already set.
- LLM requests send the configured key and messages to the configured OpenAI-compatible base URL, which defaults to https://api.openai.com/v1.
- The MCP server launches its own CLI helper to handle requested tool calls.
- The version-change hints report no new lifecycle scripts or dependencies; prepublishOnly runs build and tests.
Evidence against
- The MCP i18n_run tool can modify the selected project when called, as described in its tool description.
- The MCP helper inherits the environment, including any available credentials, to support the CLI's configured LLM feature.
Behavioral surface
ChildProcessEnvironmentVarsFilesystemNetwork
HighEntropyStrings
Source & flagged code
5 flaggeddist/mcp-server.jsView file
54const readline = __importStar(require("readline"));
L55: const cp = __importStar(require("child_process"));
L56: const path = __importStar(require("path"));
High
Child Process
Package source references child process execution.
dist/mcp-server.jsView on unpkg · L5454Cross-file remote execution chain: dist/mcp-server.js spawns dist/config.js; helper contains network access plus dynamic code execution.
L54: const readline = __importStar(require("readline"));
L55: const cp = __importStar(require("child_process"));
L56: const path = __importStar(require("path"));
...
L171: // 每行一个 JSON，行尾必须有 \n（MCP stdio 帧分隔）
L172: process.stdout.write(JSON.stringify(msg) + '\n');
L173: }
...
L191: return new Promise((resolve) => {
L192: const cliPath = path.join(__dirname, 'cli.js');
L193: const child = cp.spawn(process.execPath, [cliPath, ...args], {
L194: cwd: process.cwd(),
L195: env: process.env,
L196: windowsHide: true
High
Cross File Remote Execution Context
Source spawns a local helper that also contains network and dynamic execution context; review data flow before blocking.
dist/mcp-server.jsView on unpkg · L54package.jsonView file
Findings
1 Critical3 High2 Medium6 Low
CriticalPrevious Version Dangerous Deltadist/config.js
HighChild Processdist/mcp-server.js
HighCross File Remote Execution Contextdist/mcp-server.js
HighSemantic Analysis Limitedpackage.json
MediumNetwork
MediumEnvironment Vars
LowNon Install Lifecycle Scripts
LowScripts Present
LowFilesystem
LowHigh Entropy Strings
LowUrl Strings
LowAi Review Evidencepackage.json
Affected versions and remediation
This report applies to code-i18n-agent@0.1.9.
See all versions of code-i18n-agent for other recorded verdicts.
- Review the evidence and your use of code-i18n-agent@0.1.9 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.