Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed architecture-planning and project-scaffolding workflow, with only minor cautions around broad triggers and file creation.
Install only if you want architecture-selection help during project initialization. Expect it to ask project-context questions, use web research, and guide creation of project directories and ADR documentation; review any separate external plugin or scripts before running them.
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
Use this when the user has a clear context and wants a fast recommendation.
The trigger list includes very broad terms such as "architecture," "research," "decision-making," and "best-practices," which are common in ordinary development conversations. This can cause the skill to activate outside its intended scope, injecting unsolicited workflow steps, research requirements, or architecture-selection behavior into unrelated tasks.
This markdown file states that the template customizer creates a directory structure, which can affect user files and project layout. The description does not include any warning, confirmation note, or caution about where output will be written or that existing files may be impacted.
No suspicious patterns detected.