T09 · Insecure Skill Coding Practices
- Location
scripts/simple-verify.js:50- Finding
Shell Command Injection Through a User-Controlled CLI Filename
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This adversarial testing skill is purpose-aligned, but its verifier can run target-controlled commands on the host without enforcing the sandboxing it promises.
Install only if you will run it in a disposable, credential-free sandbox. Avoid using it on untrusted repositories or production paths until command execution is isolated and the CLI filename handling is fixed.
scripts/simple-verify.js:50Shell Command Injection Through a User-Controlled CLI Filename
scripts/simple-verify.js:84Untrusted npm Lifecycle and Build Scripts Execute Without Isolation
The document presents all operational guidance in Chinese and uses mandatory language throughout, but it does not state that the skill is region-specific or provide any user opt-in for language preference. This can violate language/locale policy expectations when skills should not force a specific language without user choice or a documented justification.
The trigger conditions are overly broad ('high-risk changes', 'core functionality', 'security-related code', or 'user-requested verification') and can cause the skill to run in many unintended contexts. Because this skill explicitly promotes destructive/adversarial testing and real command execution, ambiguous invocation increases the chance of unnecessary risky actions, resource consumption, or disruptive validation outside appropriately scoped environments.
This markdown file contains user-facing instructions exclusively in Chinese, including installation, usage, and operational guidance. Under the language/locale policy, forcing a specific language without user opt-in or a documented regional constraint is a natural-language policy violation.
This JavaScript file uses Chinese for the top-level description, comments, and CLI output such as usage/help text, but provides no opt-in, language selection, or justification that the skill is intended only for a Chinese-speaking audience. That creates a natural-language locale policy issue because the skill effectively enforces a specific language for all users.
The natural-language description is entirely in Chinese and does not indicate that other languages are supported or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a locale/language policy concern.