Back to skill

Security audit

Expert Role

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only expert-role skill that changes answer style and structure, with no code execution, persistence, credential access, or hidden data flow found.

Before installing, confirm you want a broad expert-analysis writing style to activate for complex questions. Non-Chinese users may need translation to fully review the documentation, but the inspected skill does not request sensitive access or perform actions outside answer generation.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is broadly framed around providing deep professional analysis, which can match a wide range of normal user requests without clear boundaries. This increases the chance of unintended activation and overbroad role-steering, causing the agent to apply hidden behavioral instructions in contexts where the user did not explicitly request this mode.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger table uses subjective conditions such as 'complex problem analysis' and 'high-quality output' without concrete thresholds or exclusions. In a skill-routing system, this ambiguity can cause the skill to activate for many ordinary queries, giving it excessive influence over responses and making prompt-scope control weaker.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The entire skill file, including headings and usage instructions, is written in Chinese and provides no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file contains user-facing guidance only in Chinese, which can amount to a language/locale policy violation when no opt-in or alternative language is provided. The content does not indicate that the skill is intentionally region-specific or that users can choose their preferred language.

Content

No source excerpt is available for this finding.