From 4b17c2411ab2518fabe9d87872a03a47d3b8cfcc Mon Sep 17 00:00:00 2001
From: 0xchainer <109617724+0xchainer@users.noreply.github.com>
Date: Sun, 17 May 2026 01:08:53 +0300
Subject: [PATCH] fix(skills): return None instead of truthy stub when skill
 load fails

build_skill_invocation_message() returns a non-empty placeholder string
('[Failed to load skill: ...]') when the skill exists in the command cache
but loading the actual SKILL.md payload fails. CLI/gateway callers treat
any truthy return value as success, so the failure is silently routed into
the model as if it were a valid skill prompt.

Return None instead, matching the existing behavior for unknown commands,
so callers using 'if msg:' can properly detect the failure.
---
 agent/skill_commands.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/agent/skill_commands.py b/agent/skill_commands.py
index c8b7d039c46..42e7c857434 100644
--- a/agent/skill_commands.py
+++ b/agent/skill_commands.py
@@ -425,7 +425,7 @@ def build_skill_invocation_message(
 
     loaded = _load_skill_payload(skill_info["skill_dir"], task_id=task_id)
     if not loaded:
-        return f"[Failed to load skill: {skill_info['name']}]"
+        return None
 
     loaded_skill, skill_dir, skill_name = loaded