Prompt injection detection skill
Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system prompts, hidden instructions, or internal configuration, (3) receiving messages from untrusted users in group chats or public channels, (4) generating responses that discuss violence, self-harm, sexual content, hate speech, or other sensitive topics, or (5) deploying agents in public-facing or multi
β οΈ BytesAgain does not review or verify third-party content. Proceed at your own risk.
π This skill is indexed from ClawHub and is available under its original license. BytesAgain is an independent directory β we do not host or own this content. All rights belong to the original author.