ClawHub
Back to skill

Security audit

uyghur-ai

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Uyghur/Chinese translation and chat integration that sends requested text or documents to its API service using a configured API key.

Install only if you are comfortable sending the text, prompts, or document text layers you choose to translate to the AI Skills service. Avoid uploading confidential documents unless you have approval, and store the API key only in the intended OpenClaw environment configuration.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The entire skill guidance is written only in Chinese, which imposes a specific language/locale on users and implementers without any opt-in or alternative language path. Under the stated policy, forced language use is a natural-language policy violation unless the locale restriction is explicitly justified.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The text states that the interface is used for Uyghur-language Q&A, explanation, polishing, summarization, and creation, which imposes a language-specific constraint in the skill description. Under the policy, forcing a specific language without an explicit user opt-in or documented justification is a natural-language policy violation.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
Natural-language content in the title, examples, and sample payloads assumes a specific language/locale context and does not indicate user choice or that the skill is intentionally limited to this locale. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale constraint is clearly documented and justified.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
API_ROOT="${AI_SKILLS_API_URL:-https://ai-skills.open-idea.net}/api/v1"

curl --fail-with-body "$API_ROOT/uyghur-ai/translation" \
  -H "Authorization: Bearer $UYGHUR_AI_SKILL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: uyghur-translate-001" \
Confidence
91% confidence
Finding
The example shows an authenticated external request that sends user-provided content and a bearer token to a remote API endpoint. In context this is core functionality, but it is still a real external-transmission risk because users may not realize that prompts or translated text leave the local environment and are handled by a third-party service.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The PDF translation example performs an authenticated file upload to a remote service but does not explicitly warn that the document contents and bearer token are being transmitted off-host. In a translation skill, this behavior is expected, but the missing disclosure increases the risk of users unintentionally sending sensitive documents or credentials to an external endpoint.

Natural-Language Policy Violations

Medium
Confidence
86% confidence
Finding
The routing guidance is written in natural language and repeatedly constrains behavior to Chinese and Uyghur, including 'strict translation' and Uyghur-specific handling. Because the file does not state that users can choose another language or that this locale restriction is optional, it appears to force a specific language policy without user opt-in.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The entire skill description is written only in Chinese and specifies behavior exclusively for `zh` and `ug`, with no indication that users may choose another language for interaction or documentation. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless clearly justified as region-specific, which is not stated here.

Static analysis

No suspicious patterns detected.