Back to skill

Security audit

头脑超级风暴

Security checks for vulnerabilities and agentic risk

Overview

This is a brainstorming workflow skill that is broadly worded but does not contain hidden execution, credential access, exfiltration, or destructive behavior.

Install this if you want a Chinese-language brainstorming workflow that may review project context and create a committed design document after validation. If you prefer direct implementation, another language, or no automatic git commits, set those expectations explicitly before using it.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 skill declares it 'must be used before any creative work,' which is an overly broad activation rule that can hijack normal agent behavior and force invocation in many unrelated contexts. This increases the chance of unnecessary tool/skill routing, creates workflow lock-in, and may let this skill override user preference or more appropriate domain-specific skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill content is written to operate entirely in Chinese and does not provide user choice or a justification for enforcing that language. In a multilingual agent environment, this can cause instruction mismatch, reduce transparency for users and reviewers, and lead to misunderstandings in planning, approval, or downstream implementation steps.

Content

No source excerpt is available for this finding.