The Agent Skills Directory

[SAFE]: The skill documents defensive coding practices, specifically input sanitisation and schema validation at trust boundaries, which mitigates common injection vulnerabilities in the target application.
[PROMPT_INJECTION]: The skill contains a 'Response Format' block that instructs the agent to structure its output in a specific way. This is a standard design pattern for AI agent skills to ensure consistent behavior and does not represent a malicious attempt to bypass safety guidelines or override system instructions.

data-validation