The Agent Skills Directory

[SAFE]: The skill is entirely instruction-based and does not contain any executable scripts or binary files. Its primary function is to guide an agent through generating a markdown specification file (spec.md) based on a provided template.
[DATA_EXFILTRATION]: No network operations or data exfiltration vectors were detected. The skill operates exclusively on local project files (specs/ and references/).
[COMMAND_EXECUTION]: The instructions do not invoke any shell commands or external processes. It uses standard file-writing behavior expected of an AI agent.
[PROMPT_INJECTION]: No malicious instruction overrides or safety bypass attempts were found. The 'IMPORTANT' markers used in the text are benign instructional guidelines for the agent's logic flow.
[CREDENTIALS_UNSAFE]: No hardcoded credentials or attempts to access sensitive system directories (like .ssh or .aws) were identified.

spec-specify