Back to browse
GitHub Repository

Secure every action your AI agents take (Claude Code, Codex, MCP). Blocks secret access, gates risky commands, and enforces allow/deny/approval before actions run.

6 starsGo

Solution for Prompt Injection of AI Agents

by prudhvinomos·Mar 27, 2026·3 points·0 comments

AI Analysis

●●SolidBig BrainBold Bet

Execution firewall for AI agents before prompt injection causes real damage.

Strengths
  • Agent-agnostic and model-agnostic design works across MCP and HTTP integrations
  • Deterministic policy decisions with manual approval routing for sensitive actions
  • Audit evidence and output redaction provide compliance trail for governed actions
Weaknesses
  • Only 2 stars—very early stage with unproven real-world adoption
  • AI agent security is emerging space; standards and best practices still forming
Category
Target Audience

Teams deploying AI agents with access to real systems

Similar To

Lakera Guard · Protect AI · HiddenLayer

Post Description

If you do not govern agent actions your safety boundary is at risk. Prompt injection, tool misuse, and over-broad credentials turn into real side effects fast. Nomos applies zero-trust controls at the moment an agent tries to do something real. It does not restrict the model's reasoning. It controls what the agent is actually allowed to do.

Similar Projects

Security●●●Banger

MVAR – Deterministic sink enforcement for AI agent

IFC + capabilities block prompt injection at execution sinks, not input filters—40yr research applied.

Big BrainWizardry
ShawnC21
113mo ago
Security●●●Banger

Aegis – Open-source pre-execution firewall for AI agents

Interceptor layer blocks SQL injection and shell injection before agents execute them.

Big BrainZero to OneSolve My Problem
AEGIS_JB
202mo ago
SecurityPass

ClawShield – Open-source firewall for agent-to-agent AI communication

This feels like the first serious attempt to treat agent-to-agent chatter as a network security problem: 16+ prompt-injection signatures (with recursive base64 decoding), AST static analysis of skills via acorn/estree, and sandboxed dynamic checks are concrete, non-trivial defenses. The repo shows real engineering (Docker, CI, security scans, 181 tests) — the missing piece is real-world performance and adoption, but if you run agent fleets this is worth poking at.

WizardryNiche Gem
Joe_DNAI
223mo ago