claude-flow
Verified · 14 days agoAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Agent Skill & Config Security Audit
Verified · todayScan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.
Install
claude mcp add --transport http agent-skill-audit-mcp https://agent-skill-audit-mcp.mcpize.run/mcp
Our take
This server scans agent skills and configuration files for risks such as hidden Unicode, prompt injection, and exfiltration patterns. It is aimed at developers auditing AI-agent setups, and while the problem space is valuable, the absence of adoption signals means results should be treated as an additional review aid rather than a complete security assessment.
Verification record
- today
- 0
- today
- no
- MIT
- 2026-10-01
More in ai
browse all →tldraw
Verified · 15 days agoDraw and visually collaborate with your agents on tldraw's canvas.
Codebase Memory
Verified · 5 days agoCodebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
OpenMetadata
Verified · 33 days agoOfficial OpenMetadata MCP: 21 read and write tools for search, lineage, data quality, governance.
mobilerun
Verified · 17 days agoControl real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
PraisonAI
Verified · 4 days agoAI Agents Framework with Self Reflection and MCP support