Skip to content

OpenAI's Codex Security CLI and TypeScript SDK for finding, validating, and fixing security vulnerabilities. npm: https://www.npmjs.com/package/@openai/codex-security

fix(skills): limit fix-finding to security vulnerabilities (#923)

Tiffany Citra36280ba6a1b0
diff --git a/plugins/codex-security/skills/fix-finding/SKILL.md b/plugins/codex-security/skills/fix-finding/SKILL.md
index 1d54d6834..007c1785c 100644
--- a/plugins/codex-security/skills/fix-finding/SKILL.md
+++ b/plugins/codex-security/skills/fix-finding/SKILL.md
@@ -1,6 +1,6 @@
---
name: fix-finding
-description: Use when the user explicitly asks to fix and verify a validated or plausible security finding. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.
+description: Use only when the user explicitly asks to fix and verify a validated or plausible security vulnerability. Do not use for ordinary bug fixes, correctness or design review findings, general validation, or full PR, commit, branch, patch, or repository scans.
---
# Fix Finding
diff --git a/plugins/codex-security/skills/fix-finding/agents/openai.yaml b/plugins/codex-security/skills/fix-finding/agents/openai.yaml
index e69ed78dd..cf7ed71c9 100644
--- a/plugins/codex-security/skills/fix-finding/agents/openai.yaml
+++ b/plugins/codex-security/skills/fix-finding/agents/openai.yaml
@@ -1,4 +1,4 @@
interface:
- display_name: "Fix Finding"
+ display_name: "Fix Security Finding"
short_description: "Fix and verify a given security finding"
default_prompt: "Use $fix-finding to fix a given security finding and verify the issue no longer reproduces."