mcpware

IntentProbe — Security skill for Claude Code

Security community

Activation-probe security scanner for AI agent tooling.

How to install IntentProbe

This entry records only its repository, not the path inside it, so there is no exact command to give. Open mcpware/IntentProbe and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What IntentProbe does

Activation-probe security scanner for AI agent tooling. Reads a model's internal activations to detect poisoned MCP servers, skills, and packages before install.

Alternatives in Security

Rolecraft — The security-first skill manager for AI agents — every install runs a security scan 75 ★
Claude Skill Antivirus — Security scanner for Claude Code Skills — 9 engines detect malicious patterns, data exfiltration, dangerous op 64 ★
DeepSafe Scan — Preflight Security Scanner For AI Coding Agents — Full-featured preflight security scanner across 5 dimensions: Posture (config), Skill (skills & MCP), Memory ( 62 ★

README

IntentProbe

A local scanner for MCP servers, tools, and skills. It reads a frozen model's activations, not just the text — so it catches attacks worded in ways a text classifier never saw.

Text scanners read words. IntentProbe reads activations.

What it is

IntentProbe runs a tool description or prompt through a frozen local model (Qwen2.5-0.5B), reads a few mid-layers, and scores the mean-pooled activation vector with a small logistic probe (~22 KB). Most scanners read the text itself: patterns, classifiers, rules, or "ask an LLM". This reads the host model's internal state instead.

The point of doing it this way is generalization. When you train a text classifier on attack examples and then face attacks from a source it never saw, the vocabulary often doesn't transfer and recall collapses. The probe holds up better across sources, because it keys off how the mo