Back to skill

Security audit

Xiao Chuang You Literature

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese literature guidance skill with no code, persistence, or hidden access requests.

Install this if you want a Chinese-language literature assistant for poetry, reading lists, and calligraphy guidance. Be aware it may activate on broad reading or literature prompts and may steer answers toward its Chinese literary style.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation description is broad enough to match common user requests about reading, books, or recommendations that may not specifically require this literature skill. Over-broad routing can cause unintended activation, leading the assistant to apply this skill's fixed style and domain assumptions in contexts where a different skill or general handling would be safer or more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list contains very generic terms such as '诗', '词', '读书', '阅读', and '推荐书', which are likely to appear in many unrelated conversations. This raises the chance of accidental activation and misrouting, which can override better-matched skills or cause irrelevant, inflexible responses.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description, role instructions, trigger words, and response norms all assume Chinese-language interaction, but the file does not state that this is an opt-in locale-specific skill or offer an alternative language choice. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.