Back to skill

Security audit

Idea Darwin 中文版

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language idea-iteration skill that reads and writes project-local idea files, with no executable code, network behavior, credential handling, or hidden persistence found.

Install this if you want a Chinese-language workflow that organizes and evolves ideas in local project files. Use it in a workspace where creating and updating cards, reports, config.yaml, and graph data is acceptable, and invoke it intentionally for idea-management 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
  • 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 (6)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The listed natural-language trigger phrases are broad brainstorming-related expressions without exclusion rules, so ordinary conversation about ranking or iterating ideas may spur unintended skill activation. While this does not directly introduce code execution, it can misroute user intent and cause unnecessary processing of local files or stateful project changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

文件在名称和开头描述中明确标注“zh”“中文版”,但未说明这是用户自选版本,或在交互中提供语言切换/确认。按规则,这可能构成未经用户选择即施加特定语言/locale 的自然语言策略问题。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The listed natural-language trigger phrases are broad brainstorming-related expressions without exclusion rules, so ordinary conversation about ranking or iterating ideas may spur unintended skill activation. While this does not directly introduce code execution, it can misroute user intent and cause unnecessary processing of local files or stateful project changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains natural-language instructions exclusively in Chinese, and nowhere indicates that users may choose another language or that the skill is intentionally region-specific. Under the language/locale policy rule, forcing a specific language without opt-in is a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The entire prompt file is written as mandatory Chinese-language operating instructions, including fixed output labels and report templates. There is no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-only regional context, which creates a language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The markdown template’s heading and all instructional text are written in Chinese, which implicitly constrains use to a specific language. There is no indication that users may choose another language and no documented justification that this template is intentionally region-specific.

Content

No source excerpt is available for this finding.