ClawHub
Back to skill

Security audit

mongolian-ai

Security checks for vulnerabilities and agentic risk

Overview

This skill is a purpose-aligned Mongolian language API integration, with clear paid external processing behavior and no evidence of hidden persistence, local compromise, or unrelated data access.

Install only if you are comfortable sending the content you ask it to process, including files, images, and audio, to the AI Skills platform and paying from that platform wallet. Do not use it for secrets, regulated data, or confidential documents unless your organization permits that provider and data flow.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (10)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly handles OCR, speech, chat, and document translation through an external platform API, but it does not clearly and prominently disclose that user-provided text, images, audio, and files will be transmitted off-platform for third-party processing. This can lead users to share sensitive content under incomplete informed consent, creating privacy, compliance, and data-handling risks even if the external service is legitimate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file mandates behavior in a single language/locale context by presenting all operational instructions only in Chinese. Under the stated policy, forcing a specific language without user opt-in or clear justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation states that the system message can require replies to be only in Chinese, traditional Mongolian, or Cyrillic Mongolian. This imposes a language/locale constraint in the skill instructions without indicating any user choice, opt-in, or documented regional justification.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/HTTP-REQUESTS.md (reported line 6)May include surrounding context.

七种能力及异步提交均使用 HTTPS、Authorization: Bearer 与 Idempotency-Key。示例中的 ID 每个新操作必须不同；重试原请求时保留原 ID。不要在日志中打印密钥或正文。任务查询与音频下载只需 Authorization。

sh
curl -sS -D /tmp/mongolian-response-headers \
  https://ai-skills.open-idea.net/api/v1/mongolian-ai/translation \
  -H "Authorization: Bearer ${MONGOL_AI_SKILL_API_KEY:-$AI_SKILLS_API_KEY}" \
  -H "Idempotency-Key: unique-translation-request-id" \

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example request includes a system instruction saying '只用西里尔蒙古文回答。' ('answer only in Cyrillic Mongolian'). This is a natural-language locale constraint with no indication of user choice or opt-in, which matches the policy-violation category for forced language selection.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documentation instructs the agent to send OCR-recognized text to a separate /translation endpoint when translation is requested, but it does not require a user warning or explicit consent before this secondary disclosure. OCR output may contain sensitive personal, financial, or credential data from uploaded images, so forwarding it to another service boundary increases privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation instructs sending user-provided text to an external translation endpoint but does not warn that the content leaves the local system and is transmitted to a third-party service. This can lead users or downstream agents to submit sensitive text such as personal data, credentials, or confidential documents without informed consent, creating a privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file’s natural-language instructions are entirely in Chinese, which can impose a language constraint on users or integrators who do not read Chinese. The policy requires flagging language or locale restrictions unless the skill explicitly offers a language choice or clearly documents a justified regional constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The file states that the language parameter defaults to mn, which imposes a specific locale choice when the user does not explicitly select one. The documentation does not indicate user opt-in or present the language choice neutrally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The natural-language instructions in this file are entirely in Chinese, which can impose a language constraint on users or operators without opt-in. The file does not indicate that the skill is intentionally limited to Chinese-speaking users or provide an alternative language option.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.