The Agent Skills Directory

[SAFE]: The skill uses standard platform hooks (UserPromptSubmit, PreToolUse, PostToolUse) to implement its core functionality. These hooks are used to inject instructions to the agent and trigger media playback based on tool activity.
[COMMAND_EXECUTION]: The skill includes several shell scripts (remind-fire.sh, play-paired-sound.sh, show.sh) used for logic and media playback. These scripts are self-contained within the skill directory and use standard utilities like jq and grep for parsing, and common system players like afplay or ffplay for audio. No unauthorized command execution or privilege escalation patterns were found.
[PROMPT_INJECTION]: The skill uses a UserPromptSubmit hook to influence the agent's behavior (instructing it to "fire memes"). This is the intended primary purpose of the skill and does not attempt to bypass safety guidelines or extract sensitive information.
[EXTERNAL_DOWNLOADS]: No external downloads or remote code execution patterns were detected within the skill's scripts or instructions.

claude-brainrot