Back to skill

Security audit

Auto Translate

Security checks for vulnerabilities and agentic risk

Overview

This is a simple trilingual translation-format skill with no code execution, file access, network use, persistence, or hidden authority.

Install this only if you want responses translated into Chinese, English, and Japanese when the skill is active. It may make answers longer and may conflict with requests for a different format, but it does not appear to access local data or perform actions outside the conversation.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill mandates a fixed Chinese-first, English-second, Japanese-third output format for every matched response, regardless of the user's language, context, or safety constraints. This rigid behavior can override user preference, interfere with other instructions, and duplicate harmful, sensitive, or disallowed content into multiple languages, increasing exposure and making moderation or downstream controls less reliable.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions are very broad, including 'any multilingual output scenario' and requests to append translations after answers. This can cause the skill to activate outside the user's actual intent, leading to unsolicited transformations of responses, instruction conflicts with other skills, and possible leakage or propagation of sensitive content into additional languages.

Content

No source excerpt is available for this finding.