The Agent Skills Directory

[SAFE]: The skill implements a structured workflow for requirements elicitation using standard agent tools like AskUserQuestions and Task subagents for internal delegation. It does not attempt to execute arbitrary shell commands or download external scripts.
[DATA_EXFILTRATION]: No network operations or unauthorized data access patterns were detected. The skill writes its output (specification documents) to a local specs/ directory as described in its purpose.
[PROMPT_INJECTION]: The skill focuses on business logic and documentation templates. There are no instructions that attempt to bypass safety filters or override agent constraints. While the skill processes user-provided requirement descriptions (an indirect injection surface), it does so within a defined documentation pipeline with specific EARS and Given/When/Then templates.
[CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, or sensitive environment variable accesses were found in the instructions or reference files.

feature-forge