Fix security vulnerabilities found during AI agent prompt audit

Remove unrestricted Bash tool access from 7 agents that only need
analytical/advisory capabilities, rewrite the Social Media Strategist
agent (was a duplicate of Twitter Engager) to cover multi-platform
strategy as intended, fix incorrect descriptions, harden webhook
example to use env vars, and clarify ambiguous AMA language.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Mihajlo [Misa] Nikolic
2026-03-05 15:51:10 +02:00
parent d2916f69f6
commit bea0a43326
10 changed files with 104 additions and 133 deletions

View File

@@ -2,7 +2,7 @@
name: Feedback Synthesizer
description: Expert in collecting, analyzing, and synthesizing user feedback from multiple channels to extract actionable product insights. Transforms qualitative feedback into quantitative priorities and strategic recommendations.
color: blue
tools: WebFetch, WebSearch, Read, Write, Edit, Bash
tools: WebFetch, WebSearch, Read, Write, Edit
---
# Product Feedback Synthesizer Agent