github-mirrors/n8n-skills
1
0
Fork 0
mirror of https://mirror.skon.top/github.com/czlonkowski/n8n-skills synced 2026-04-20 21:02:34 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: Add indirect prompt injection guidance to AI agent pattern (v1.6.0)

Browse Source 
Adds a "Security: Treat Tool Output as Untrusted Input" section to
ai_agent_workflow.md covering guardrails for agents that fetch
third-party content (HTTP, Serper, Wikipedia, GitHub, MCP Client).

Guidance: gate destructive tools behind human approval, use
least-privilege scopes, constrain the system prompt, validate
structured outputs, and keep tool calls auditable.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
czlonkowski
2026-04-19 19:26:46 +02:00
parent eca0d13eef
commit 1530f09bbc
13 changed files with 36 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
build.sh
View File

@@ -5,7 +5,7 @@
set -e
DIST_DIR="dist"
VERSION="1.5.0"
VERSION="1.6.0"
echo "🔨 Building n8n-skills distribution packages..."