Back to skill

Security audit

Learn Prototype

Security checks for vulnerabilities and agentic risk

Overview

This is a coaching-only learning skill that gives process guidance and does not request sensitive access, persistence, or execution privileges.

Install this if you want a Chinese-language coaching pattern for learning by building rough prototypes and improving them. Be aware that it may activate for broad 'make/research/improve X' requests, so users who prefer narrower skill routing or non-Chinese instructions may want the publisher to clarify scope and language 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says the skill should be used when a user wants to do or research 'X', improve a skill, optimize 'X', or doesn't know where to start. These trigger examples are extremely broad and lack clear scope boundaries or exclusion conditions, which could cause unintended invocation for many ordinary conversations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill's description and instructional content are entirely in Chinese, with no indication that language choice is optional or limited to a justified region-specific context. This can violate language or locale policy because it implicitly constrains interaction to a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The '何时用' section says to use the skill whenever a user wants to build, research, or improve something, but it does not define when this skill should be preferred over other general learning or coaching skills. Without constraints or negative examples, the activation condition remains ambiguous.

Content

No source excerpt is available for this finding.