Back to skill

Security audit

伪中国语趣味翻译

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only novelty translation skill with no code execution, persistence, credential access, or hidden high-impact behavior.

Install this if you want a playful pseudo-Chinese/Japanese-kanji style translator. Be aware that it prefers a fixed annotated format and may be less suitable for ordinary concise translation unless you ask the agent to avoid using it.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The mandated fixed output format forces Chinese/Japanese-labeled sections and does not allow adaptation to user locale, accessibility needs, or downstream system expectations. This is primarily a usability and integration risk: it can produce unwanted content structure, complicate orchestration, and leak extra annotations when only a simple translation was requested.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger is broad enough that the skill may activate on generic Chinese translation requests rather than only when the user explicitly asks for pseudo-Chinese style output. That can cause unintended invocation, incorrect task routing, and user confusion, especially if the agent overrides a normal translation request with this novelty transformation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description and opening instructions state that the skill translates Chinese into pseudo-Chinese style and repeatedly frame usage as operating specifically on Chinese text. This is a natural-language locale/language constraint presented as mandatory behavior, with no user choice or opt-in mechanism described.

Content

No source excerpt is available for this finding.