From 1e2443fb9056972b3a1a5a3a05fa7cd484395bf1 Mon Sep 17 00:00:00 2001 From: Alex Date: Tue, 14 Apr 2026 11:49:13 +0100 Subject: [PATCH] Update .github/INCIDENT_RESPONSE.md Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --- .github/INCIDENT_RESPONSE.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/INCIDENT_RESPONSE.md b/.github/INCIDENT_RESPONSE.md index f2b16bd8..419c2fd1 100644 --- a/.github/INCIDENT_RESPONSE.md +++ b/.github/INCIDENT_RESPONSE.md @@ -73,7 +73,7 @@ This playbook describes how maintainers respond to confirmed or suspected securi Treat confirmed AI-specific abuse as security incidents: -- Prompt injection causing sensitive data exfiltration (from tools that dont belong to agent) -> **High** +- Prompt injection causing sensitive data exfiltration (from tools that don't belong to the agent) -> **High** - Cross-tenant retrieval/isolation failure -> **High** - API key disclosure in output -> **High**