The Agent Skills Directory

[SAFE]: No security issues detected. The skill instructions focus on a conversational interview process and legitimate codebase exploration.
[DATA_EXPOSURE]: The skill instructs the agent to "explore the codebase" to answer questions. While this involves reading local files, there are no instructions or tools provided to exfiltrate this data or access sensitive credentials outside the project scope.
[INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface as it reads data from the codebase. However, it lacks capabilities such as network access, file writing, or command execution that would allow an attacker to exploit this ingestion surface.

grill-me