The Agent Skills Directory

[SAFE]: The skill is a purely instructional prompt that guides the agent through a user interview process. It does not contain any executable code, scripts, or network requests.
[DATA_EXPOSURE]: The skill instructs the agent to read project files like README.md, AGENTS.md, or CLAUDE.md to gather context. This is a standard operation for project-based AI agents and does not involve unauthorized data access or exfiltration.
[COMMAND_EXECUTION]: There are no shell commands, system calls, or external script executions defined in the skill.
[PROMPT_INJECTION]: The instructions do not attempt to bypass safety guardrails or override system-level instructions. The 'Must NOT' section explicitly prevents the agent from inventing facts or making unauthorized changes to existing content.

fstack-interview