Security Fencing

Canonical prompt-injection hardening block for agents that analyze untrusted content (source code, CI logs, workflow files). Use when authoring an agent that reads untrusted input — copy the appropriate variant verbatim into the agent body; only pure output-only agents (no file reading, no untrusted input) are exempt.

kinginyellows Updated 0 repo stars

File contents

kinginyellows/yellow-plugins commit a38ae1f25f

Frequently asked questions

npx get-skill add kinginyellows/security-fencing