xdoc-translation
v1.0.2提供文档和文本翻译服务,支持多种文件格式、高质量翻译及术语库和记忆库管理。
⭐ 1· 107·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, manifest, and SKILL.md consistently describe a document/text translation service (document upload, translation, glossaries, translation memory) against https://translation.x-doc.ai/api/open_api/v1. Required credential (XDOC_API_KEY) is appropriate and expected for this purpose.
Instruction Scope
Runtime instructions focus on creating upload URLs, uploading files, submitting translation jobs, polling status, and downloading results. This necessarily transmits user documents to the external Xdoc service — expected for a translation skill but a privacy consideration. The SKILL.md does not instruct the agent to read unrelated local files, secret stores, or other environment variables beyond the declared API key.
Install Mechanism
Instruction-only skill with no install spec and no bundled code; nothing is written to disk by an installer. Lowest-risk install posture.
Credentials
Only a single API key (XDOC_API_KEY) is required and documented. That is proportionate for a hosted translation API. No unrelated credentials or config paths are requested.
Persistence & Privilege
Skill does not request always: true and uses the platform default for model invocation. It does not claim to modify other skills or system settings. Autonomous invocation is allowed by default (platform behavior) but not unusual here.
Assessment
This skill appears to be what it says: a wrapper for a third‑party translation API. Before installing or using it, consider: (1) Documents you upload will be sent to https://translation.x-doc.ai — do not upload highly sensitive or regulated content unless you trust their policies and contracts; (2) store XDOC_API_KEY securely and rotate/revoke it if exposed; (3) verify the vendor (https://x-doc.ai) and privacy policy (manifest claims 7‑day retention) if you care about retention/processing; (4) if you don't want the agent to call the skill autonomously, disable or restrict autonomous invocation via your platform controls. If you need stronger assurances (enterprise SLA, data residency, guaranteed deletion), contact the vendor before sending sensitive data.Like a lobster shell, security has layers — review code before you run it.
latestvk97083cdk5kxvf3xgm8dp21n5h833xmv
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
