Back to skill

Security audit

文言内核

Security checks for vulnerabilities and agentic risk

Overview

This is a style-only skill that changes internal phrasing and keeps user-facing answers concise, with no code, data access, persistence, or external execution.

Install this only if you want the agent to default toward concise answers and classical-Chinese-style internal task framing. Users who prefer explicit opt-in style changes may find its trigger scope too broad, but the reviewed artifact does not show data access or executable behavior.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest lists trigger phrases such as '内部都用文言文,回答正常输出' and 'think internally in wenyanwen, answer in my language' that overlap with normal user requests about response style. Because these are not unique invocation commands, the skill may activate accidentally when a user is merely describing preferences, leading to hidden behavior changes without clear consent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest lists trigger phrases such as '内部都用文言文,回答正常输出' and 'think internally in wenyanwen, answer in my language' that overlap with normal user requests about response style. Because these are not unique invocation commands, the skill may activate accidentally when a user is merely describing preferences, leading to hidden behavior changes without clear consent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file repeatedly states that the skill should be used routinely unless there is a special reason not to. That broad defaulting weakens boundary discipline and encourages application outside its intended niche, which is risky because the skill modifies internal planning and response style across many tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The '默认适用' section covers many categories and ends with a catch-all for nearly all transactional, informational, and decision-oriented problems. Such expansive scope makes unintended invocation much more likely and can interfere with other specialized skills or safer defaults that should govern those interactions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file states that regardless of whether the user uses Chinese, English, Japanese, or Spanish, internal processing should always follow a Chinese classical-language framework. This is a language policy constraint applied universally rather than offered as an opt-in or justified region-specific requirement.

Content

No source excerpt is available for this finding.