Back to skill

Security audit

Creative Lateral Thinking

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only creative brainstorming skill with no executable payload, credential handling, or hidden high-impact behavior found.

Install this if you are comfortable with a mostly Chinese-language brainstorming framework. Review the heartbeat note if your environment has strict rules around persistent memory, but this artifact does not include a mechanism to create persistence or background tasks.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The heartbeat content explicitly uses Chinese-only operational text without indicating language negotiation or user preference handling. In an agent skill, forcing a language can cause user intent mismatch, reduce transparency of autonomous behavior, and make monitoring or review harder for users and operators who do not read that language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README presents the skill description and headings in Chinese, with no indication that users can choose another language or that the skill is intentionally limited to a Chinese-language context. This creates a natural-language locale constraint that may conflict with organizational language-choice policies.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The verification protocol content is presented entirely in Chinese for the operative checklist, with no indication that users may choose another language or that the locale restriction is required for a region-specific purpose. This creates a natural-language policy concern because it implicitly enforces a language choice without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

This markdown file contains substantial user-facing content in Chinese, including the description, metadata labels, and core usage explanations, but it does not state that the skill is Chinese-language only or offer an alternative language/locale option. 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.