The Agent Skills Directory

[SAFE]: The skill defines a conversational pattern for interviewing users. All instructions are focused on the primary goal of reaching a shared understanding of a design or plan. No dangerous command execution or credential harvesting patterns were found.
[PROMPT_INJECTION]: The skill includes instructions to 'explore the codebase' to answer questions. This creates an indirect prompt injection surface where the agent could ingest malicious instructions embedded in codebase comments. This is a low-risk, inherent property of agents that read local files, and no active exploits are present in the skill code.

grill-me