Back to skill

Security audit

儿童画本制作人

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese children’s picture-book helper with no hidden code, persistence, or privileged access.

Install this if you want help making Chinese children’s picture-book storyboards and image prompts. Be aware it will tend to produce Chinese captions by default, so request a different language or format when needed.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation description is broad enough to trigger on many ordinary Chinese story or rewriting requests, which can cause the agent to invoke this skill when the user did not explicitly ask for picture-book transformation. Over-broad routing is dangerous because it can override user intent, reshape outputs into a different format, and unnecessarily steer content into image-generation workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill text directs Chinese caption rewriting as a default behavior without stating that language should follow the user's preference. This can produce outputs in an unintended language, degrade usability, and in multi-skill systems can silently override higher-level user instructions about output language or localization.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill metadata and default prompt hard-require Chinese output without indicating any user language preference, opt-in, or fallback. This can cause unexpected behavior, reduced usability, or policy/comprehension issues for users who interact in another language, though it is not a direct security exploit in the traditional sense.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.