Back to skill

Security audit

Character Intro

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only character introduction skill that may perform public web searches, with no evidence of hidden code, persistence, credential access, or destructive behavior.

Installers should expect this skill to generate detailed Chinese Markdown character profiles and to use public web searches when information is needed. Review or adjust the trigger wording if ambiguous requests like “介绍” or “是谁” could conflict with other skills, and consider adding a rule to follow the user’s language preference.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill description advertises very broad trigger phrases such as “介绍”, “是谁”, and “背景故事”, which are common in normal conversation and can match many unrelated user requests. This can cause unintended skill activation, leading the agent to override a more appropriate tool or response path and potentially perform unnecessary web searches or produce off-target content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill metadata and content are written to operate in Chinese without offering language negotiation, even though it claims support for both Chinese and English character names. In a multilingual agent, forcing Chinese output can cause incorrect handling of user intent, degrade usability, and lead to policy or routing mismatches when the user expects another language.

Content

No source excerpt is available for this finding.