Back to skill

Security audit

怎样解题

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only Chinese problem-solving coaching skill with no executable code, network behavior, credential access, or persistence.

Install this if you want a Chinese-language guided problem-solving workflow. Be aware it may activate on broad requests like asking for analysis or planning, so users who prefer direct answers or another language may need to disable it or choose a more specific skill.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad and include common requests such as '帮我分析这个问题' and '帮我规划一下', which can match many ordinary conversations outside the intended problem-solving context. This can cause unintended skill invocation, leading the agent to override more appropriate handling paths or inject an unnecessary guided workflow into unrelated tasks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains only Chinese-language instructional content, and nowhere indicates that the user can choose another language or that the skill is intentionally limited to Chinese-speaking users. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.