ClawHub
Back to skill

Security audit

json文件翻译

Security checks for vulnerabilities and agentic risk

Overview

This skill translates selected JSON fields using an online translation API, which is purpose-aligned but can expose the selected text to a third party.

Install only if you are comfortable sending the selected JSON field text to MyMemory for translation. Avoid using it on secrets, credentials, personal data, proprietary configuration, regulated data, or internal documents unless that third-party transfer is approved.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (10)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README states that network access to MyMemory API is required, but it does not explicitly warn that JSON text content will be transmitted to a third-party translation service. For a tool intended to process product data, API docs, configuration files, or datasets, this omission can cause users to unknowingly send sensitive or proprietary content off-host, creating confidentiality and compliance risk.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill describes reading local JSON files, writing translated output files, and sending content to external translation APIs, but it declares no explicit tool or permission scope. That creates an authorization ambiguity where the agent may perform file and network actions without clear least-privilege constraints or user-visible boundaries, increasing the chance of unintended data access or exfiltration.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation text is broad enough to match many ordinary requests about translating JSON, fields, or descriptions, which can cause the skill to trigger in situations where the user did not intend external processing. In this skill's context, accidental invocation is more dangerous because triggering may lead to file access and transmission of JSON contents to third-party services.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill prominently advertises online translation APIs but does not clearly warn that JSON field contents will be transmitted to external services. Users may unknowingly expose sensitive data embedded in JSON files such as internal documentation, configuration values, or personal information, making this a concrete privacy and data-exfiltration risk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description presents the feature as translating JSON files, which reasonably suggests local processing, but the implementation sends selected field contents to a third-party API. This creates a confidentiality and trust issue because users may provide sensitive JSON content without realizing it leaves their environment.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The code transmits JSON field contents to an external translation service, which is a form of data exfiltration from the local file to a third party. Even if intended for translation, this is dangerous because JSON fields may contain proprietary, personal, or confidential data and there is no validation of data sensitivity or provider trust boundary.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Field contents are sent to an external API without any explicit user-facing warning at the point of use that data will leave the system. This undermines informed consent and can lead to accidental disclosure of sensitive information embedded in JSON documents.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

The hardcoded call to https://api.mymemory.translated.net confirms external network transmission of file contents. In the context of a JSON translation skill, network access is functionally related, but it remains risky because user-supplied data is sent off-host to a third party without strong disclosure or controls.

Content

Scanner excerpt · scripts/translate_json.py (reported line 55)May include surrounding context.

python
try:
        # 使用 MyMemory API 进行翻译
        url = f"https://api.mymemory.translated.net/get"
        params = {
            'q': text,
            'langpair': f"{SOURCE_LANGUAGES.get(from_lang, 'auto')}|{LANGUAGES[to_lang]}"

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The skill text states support only for Chinese, English, Japanese, and Korean, which is a locale/language constraint expressed in natural language. The file does not explain a policy or region-specific reason for this limitation or offer broader language choice beyond the hardcoded set.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script's natural-language documentation, help text, and console output are all in Chinese, with no option to select another interface language. This creates a language-policy issue because the skill effectively forces a specific language on users without opt-in or documented justification.

Content

No source excerpt is available for this finding.