Skill flagged โ€” suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Cuihua i18n Helper

v1.0.0

๐ŸŒ AI-powered internationalization (i18n) assistant for modern web applications. Automatically extract translatable strings, generate locale files, batch tra...

โญ 0ยท 54ยท0 currentยท0 all-time
MIT-0
Download zip
LicenseMIT-0 ยท Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report โ†’
OpenClawOpenClaw
Suspicious
medium confidence
โ„น
Purpose & Capability
Name/description and included code are coherent with an i18n extraction/locale-management tool (Node script, React/Vue extraction patterns, locale files). However the SKILL.md advertises batch translation via DeepL, Google, OpenAI, Azure and LibreTranslate but the skill declares no required environment variables or primary credential. Real provider integrations normally require API keys/endpoint config, so either the code expects you to supply keys at runtime (not declared) or the translation step may rely on the agent's own LLM rather than explicit provider APIs. This discrepancy is unexplained.
โ„น
Instruction Scope
Runtime instructions ask the agent to scan source folders (e.g., src/) and run node i18n-helper.js which will read project files and write/update locale JSON files and potentially auto-fix issues (--fix). That behavior is consistent with the stated purpose, but it does give the skill authority to read and modify project files. The SKILL.md does not instruct the agent to read unrelated system paths or secrets, nor does it grant broad open-ended data collection, but the file-modification capability is significant and should be run on a trusted or sandboxed copy first.
โœ“
Install Mechanism
No install spec โ€” instruction-only with included Node script. This is low-risk compared to downloading and executing archives from external URLs. The agent will rely on the existing node binary which is declared as required.
!
Credentials
The skill lists multiple third-party translation providers (DeepL, Google, OpenAI, Azure), but requires no environment variables or credentials in its metadata. Provider access normally requires API keys and endpoint configuration (e.g., DEEPL_API_KEY, GOOGLE_API_KEY, OPENAI_API_KEY, AZURE_*). The absence of declared env vars is a mismatch: the agent may prompt for credentials at runtime, expect global system creds, or contain hidden/undocumented network calls. This is the main proportionality concern.
โœ“
Persistence & Privilege
always is false, user-invocable is true, and there are no declared config paths or requests to change other skills. The skill will write locale files within the project (local file persistence), which is expected for its purpose. No system-wide persistence or cross-skill config changes are indicated.
What to consider before installing
This skill appears to do what it says โ€” extract strings and manage locale files โ€” but review a few things before you run it on a real repo: - Credentials: The documentation says it supports DeepL/Google/OpenAI/Azure, but the skill metadata declares no API keys. Expect the tool to ask you for provider keys at runtime or to attempt network calls; do not paste secrets into prompts without verifying where they are stored/used. - File writes: The tool will read your source tree and write/update locales/*.json and can auto-fix code. Run it first on a copy or in a branch so you can review changes. - Network behavior: Inspect the rest of i18n-helper.js (the truncated portion) for any outbound network calls or hard-coded endpoints before giving it network access. If it tries to call translation APIs, ensure you provide credentials via safe environment variables and not in a chat. - Least privilege: If you only need extraction, avoid enabling automatic translation or --fix until you confirm behavior. Prefer local/self-hosted providers (LibreTranslate) if you want to avoid sending strings to third-party services. What would change this assessment: seeing explicit code that contacts translation provider endpoints and where it expects API keys (or evidence that no provider integration exists). If the script includes clear, well-documented environment variable names for provider credentials and instructions on secure usage, the proportionality concern would be reduced.

Like a lobster shell, security has layers โ€” review code before you run it.

latestvk97cbg8h2r2ez361a8c9a2kqqs83h6ss

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

Binsnode

Comments