Security audit

Gen Code

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed code-generation skill that can modify project files, with no evidence of hidden execution or data exfiltration, but users should review generated database configuration.

Install only if you want a Chinese-language code-generation workflow that can read project docs/source and write substantial repository changes. Use explicit /gen-code commands, review planned file changes before accepting auto or scaffold modes, and replace any generated plaintext database password template with environment variables or local-only secret handling.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: scaffold-templates.md:80
Finding: Generation of Plaintext Development Database Credentials
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The file’s natural-language description and all user-facing instructions are presented exclusively in Chinese, with no indication that the user may choose another language or that the skill is intentionally limited to a Chinese-only context. Under the language/locale policy, forcing a specific language without opt-in is a policy concern.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The alias list includes generic activators like “写代码”, “实现功能”, and “生成代码”, which are common user intents that may arise in many unrelated contexts. Because this skill can scaffold projects, generate multiple files, and auto-execute tasks, broad aliases materially raise the chance of unintended invocation and repository-changing behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill defines intent-based triggers such as “生成代码”, “写代码”, and “实现.*功能”, which are broad enough to match ordinary conversational requests rather than an explicit invocation of this specific skill. In an agent environment, this increases the risk of accidental activation, causing the assistant to enter a powerful code-generation workflow that can create or modify repository files without the user's clear, scoped intent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The file title and all operational instructions are written exclusively in Chinese, indicating a fixed language/locale for the skill experience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale limitation is explicitly justified or optional.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The prompt explicitly instructs the agent to automatically update docs/tasks.md as part of normal execution, but it does not require an upfront, explicit user warning or confirmation before modifying repository files. In an agentic environment, silent state-changing writes can surprise users, corrupt task tracking, or be abused when combined with broad task scopes such as --auto or --continue.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill authorizes automatic code generation and scaffold initialization that can create or modify many project files, including root directories and framework boilerplate, without a mandatory upfront disclosure of filesystem impact. This is risky because an agent may perform broad writes in the wrong repository or create unwanted structure before the user understands the scope of changes.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 72% confidence
Finding: The entire skill file is written in Chinese and provides no indication that language choice is optional or limited to a justified region-specific context. Under the language/locale policy, a forced locale without user opt-in can be a natural-language policy violation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This markdown file describes behavior that writes .scaffold-initialized and generates scaffold files, but it does not include any explicit warning that the skill will modify the user's workspace. For markdown files, changes affecting user data or system state should be disclosed so invocation does not surprise the user.
Content: No source excerpt is available for this finding.