OWASP MCP Top 10

mentions 3 type Person feed RSS

// recent coverage 3 mentions

00:20

2026-08-31

dev.to

ai-safety

The Wildcard Scope Problem: Why MCP Configs Default to admin:* Instead of Least Privilege

A developer's static analysis of MCP configuration files reveals that many default to wildcard scopes like 'admin:*' instead of least-privilege enumerated permissions, a practice that complicates late…

09:56

2026-08-25

github.com

ai-safety

Sentinel-scan-CLI – a CLI that runs 15 prompt-injection attacks against your LLM

Ventrova released sentinel-scan-cli v1.4.8, a free open-source command-line tool that runs 15 prompt-injection and jailbreak attacks against LLM apps and MCP servers, tagging findings with OWASP LLM T…

20:52

2026-06-12

dev.to

ai-safety

I built a red-team scanner for MCP servers. Then I pointed it at the real ones.

A developer built ghostprobe, a red-team scanner for MCP servers that detects tool poisoning and the 'lethal trifecta' of data access, sink, and untrusted input. When pointed at real servers, it found…

// co-occurs with top 8 entities

sentinel-scan-cli 2 MCP 2 ghostprobe 1 GitHub 1 Invariant Labs 1 CVE-2025-54136 1 Ventrova 1 OWASP LLM Top 10 1

// topics top 6 topics

ai safety 3 ai agents 2 developer tools 2 ai tools 2 ai policy 1 ai research 1