dl-eigenart/agentshield-platform

Prompt-injection firewall for LLM agents. 6-layer pipeline (normalize, regex, MiniLM classifier, output guard, policy, audit) at <4ms p95. Python SDK + open benchmark (5,972 samples, F1 0.921).

Open on GitHub

0Stars on the repository

1Mods indexed here, across every type

3mo agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 1 mods

agentshield-mcp

dl-eigenart/agentshield-platform

MCP server Claude CodeCodexCursor

Detect prompt injection, jailbreak, and social-engineering attacks in LLM agents. Runs locally from the @eigenart/agentshield-mcp npm package. Needs 1 environment variable to run.

0 3mo ago A tokens not measured original MIT