The Agent Skills Directory

[SAFE]: The skill implements a legitimate workflow for architectural planning and requirement gathering. It guides the AI agent to conduct a structured interview to create a specification document.
[DATA_EXPOSURE_&_EXFILTRATION]: No sensitive file access or network operations were detected. The skill is restricted to 'Read', 'Write', and 'Edit' tools, which are appropriate for its documentation-focused purpose. No hardcoded credentials or secrets are present.
[INDIRECT_PROMPT_INJECTION]: The skill reads an existing SPEC.md file to continue interviews. While this involves processing external data, the scope is limited to document generation, and the risk of malicious instructions influencing critical system operations is negligible in this context.
[REMOTE_CODE_EXECUTION]: No patterns of remote code execution or package installation were identified. The skill does not attempt to execute shell commands or download external scripts.

spec