The Agent Skills Directory

[PROMPT_INJECTION]: The skill contains instructions for the model to 'silently check' its output and restricts the response to specific labels. These are functional design choices intended to reduce cognitive load for users with brain fog and are not malicious attempts to conceal information or bypass safety protocols.
[EXTERNAL_DOWNLOADS]: Documentation references for grounding include official and well-known domains like cdc.gov and simonandschuster.com. These informational links are from trusted or reputable sources and do not initiate unauthorized downloads or remote code execution.
[SAFE]: No malicious code, hardcoded credentials, or exfiltration patterns were detected. The skill is purely instructional and includes explicit boundaries to prevent providing unauthorized medical advice.

foggy-mode