The Agent Skills Directory

[PROMPT_INJECTION]: No patterns of instruction overriding, safety bypass, or role-play injection were found. The instructional language is descriptive and focused on its stated purpose of documentation generation.
[DATA_EXFILTRATION]: The skill does not contain any network operations (curl, wget, fetch) or access to sensitive file paths (e.g., .ssh, .aws). It reads local project configuration files like package.json or tsconfig.json solely to determine the project's tech stack.
[COMMAND_EXECUTION]: There is no arbitrary command execution. The skill's primary capability is writing a generated markdown file (CODING_STANDARDS.md) to the project root after user confirmation.
[EXTERNAL_DOWNLOADS]: The skill does not download any external scripts, packages, or remote code. All logic and templates are contained within the local skill directory (references/ folder).
[OBFUSCATION]: No obfuscated strings, Base64 encoding, or hidden characters were detected in any of the skill files.

coding-standards