Security audit

translator-pro

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent translation skill with a small glossary-validation helper and no evidence of hidden access, persistence, or exfiltration.

Before installing, users should be aware that the skill applies default language, locale, and formality choices when requests are underspecified. For business or legal translations, explicitly state the source language, target locale, jurisdiction, and preferred tone, and review the result rather than relying on defaults.

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

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The declared description presents an end-user translation capability, but the supplied code does not translate any text. Instead, it reads a local JSON glossary file, checks required fields, validates language codes, warns on unusual context values, and exits with a status code. This is a materially different primary purpose: glossary schema validation rather than translation. While glossary validation may support a translation system, the code chunk itself does not implement the described skill behavior.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: Defaulting ambiguous Latin-script text to English can cause silent misclassification of user input, leading to incorrect translation, loss of meaning, or mishandling of sensitive business/legal text. In a translation skill, this is more concerning because users may rely on exact language identification for formal or legal communications, and the current workflow applies the default without requiring confirmation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: Line L17 instructs the skill to 'default to neutral Latin American for broad audience unless target region specified,' which enforces a locale choice by default. Under the policy, forcing a specific language/locale variant without explicit user choice or opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The JSON template sets "target_language" to "zh-CN", which imposes a specific locale in natural language content. The file does not indicate that this locale is optional, user-selected, or justified as region-specific, so it can conflict with language/locale choice policies.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This line instructs the skill to 'Default to 您 for business and legal contexts,' which imposes a language/register choice rather than explicitly asking the user for a preferred tone or formality level. Under the policy, forced language or locale behavior without opt-in can be a natural-language policy violation unless clearly framed as optional or user-selectable.
Content: No source excerpt is available for this finding.