ClawHub
Back to skill

Security audit

tibetan-ai

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-Tibetan translation and writing helper that uses a remote API, with no hidden persistence or unrelated authority found.

Install this only if you are comfortable sending requested text or selected DOCX/PDF contents to the AI Skills service for Chinese/Tibetan processing. Do not submit confidential, regulated, or secret material unless you have authorization, and keep the API key in the configured environment variable rather than pasting it into chats or files.

SkillSpector

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

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The manifest description and README content are entirely in Chinese and describe usage only through Chinese-language prompts and workflows. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless the restriction is clearly documented and justified as region-specific.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
This markdown file contains all user-facing instructions in Chinese, with no indication that users may choose another language. The policy requires flagging language or locale constraints when a skill forces a specific language without user opt-in.

External Transmission

Medium
Category
Data Exfiltration
Content
API_ROOT="${AI_SKILLS_API_URL:-https://ai-skills.open-idea.net}/api/v1"
REQUEST_KEY="tibetan-$(date +%s)-translate"

curl --fail-with-body "$API_ROOT/tibetan-ai/translation" \
  -H "Authorization: Bearer $TIBETAN_AI_SKILL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $REQUEST_KEY" \
Confidence
87% confidence
Finding
The curl example sends user-provided text and an authorization token to an external API endpoint, creating an external data transmission path. For a translation/chat skill this is core functionality, but it is still security-relevant because users may unknowingly submit sensitive content to a third-party service.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The example shows uploading a local DOCX file to a remote API endpoint, which can transmit potentially sensitive document contents off the user's system without any explicit warning in the documentation. In a translation skill this behavior is expected, but the lack of a privacy/data-transfer notice increases the risk of accidental disclosure of confidential content.

Natural-Language Policy Violations

Medium
Confidence
82% confidence
Finding
Line L07 describes the intent as '中文与藏语严格互译', which imposes a specific language-pair behavior. Under the policy rule, forcing a language/locale behavior without offering user choice or documenting a justified constraint can be a natural-language policy violation.

Natural-Language Policy Violations

Medium
Confidence
78% confidence
Finding
The entire skill description is written in Chinese and constrains translation directions to `zh` and `bo` only, with no indication that the user can opt into another language or locale. Under the stated policy, forcing a specific language or locale without user choice can constitute a natural-language policy violation unless clearly justified as region-specific.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
All natural-language guidance in this file is presented in Chinese, including headings and usage notes, which effectively forces a specific language for users reading the documentation. There is no indication of optional locale support, translation, or justification for a Chinese-only presentation.

Static analysis

No suspicious patterns detected.