sudo-ai-git

sudo-ai-git/mcp-benchmark-hygiene

MCP server Claude CodeCodexCursor

MCP server detecting pytest config-leakage that corrupts agent-benchmark grading (deterministic, no-LLM). Runs locally from the mcp-benchmark-hygiene Python package.

sudo-ai-git/mcp-secret-scrub

MCP server Claude CodeCodexCursor

Deterministic, no-LLM MCP server that scrubs secrets from text/logs/transcripts before they enter agent context. Never leaks the value. Runs locally from the mcp-secret-scrub Python package.

sudo-ai-git/mcp-skill-sec

Skill Claude CodeCodex

A perfectly normal skill that does one harmless thing.

sudo-ai-git/mcp-skill-sec

Skill Claude CodeCodex

A skill that definitely looks like it was meant to be trusted.

sudo-ai-git/mcp-skill-sec

MCP server Claude CodeCodexCursor

MCP server auditing agent skills/system prompts against 8 malicious-skill supply-chain patterns (deterministic, no-LLM). Runs locally from the mcp-skill-sec Python package.

sudo-ai-git/mcp-verify-claim

MCP server Claude CodeCodexCursor

MCP server forcing evidence-gated, honestly-tiered claim reporting (FACT/INFERENCE/SPECULATION), deterministic no-LLM. Runs locally from the mcp-verify-claim Python package.

sudo-ai-git/agent-sec-mcp

MCP server Claude CodeCodexCursor +2

MCP server "agent-sec-mcp" as configured in sudo-ai-git/agent-sec-mcp. Runs locally from the agent-sec-mcp Python package.