Infrastructure●●Solid
TryMyClaw – Managed OpenClaw hosting with full SSH and root access
Full SSH root access on managed OpenClaw hosting beats black-box alternatives.
Solve My ProblemShip It
howardV
103mo ago
Back to browse
GitHub Repository
🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!
432 starsGo
My OpenClaw tried to exfiltrate my SSH keys, so I built a guardrail
by zcc_·Feb 24, 2026·3 points·3 comments
AI Analysis
●●●BangerSolve My ProblemBold BetZero to One
Transparent proxy intercepts agent tool calls; blocks SSH key theft before it happens.
Strengths
- •Real problem: author hit it with OpenClaw exfiltration attempt—solves a security gap agents will definitely hit.
- •Zero-code integration: point existing agent to localhost:9090, transparent blocking with no agent refactor.
- •100% local, 'auto' mode auto-detects LLM provider from model name—dead simple UX for a security tool.
Weaknesses
- •Rules appear rule-based/heuristic (README doesn't detail the blocking logic)—unclear if it catches novel exfiltration patterns.
- •Only shown working with Cursor/Claude Code; unclear support matrix for other agent frameworks.
Category
Target Audience
AI developers, security engineers running local agents (Cline, Claude Code, Cursor)
Similar To
OpenAI code interpreter sandbox · Devin's agent safety layer · Anthropic's Constitutional AI constraints
Similar Projects
Security●●●Banger
Deterministic security guardrails for Claude Code
Six shell hooks hard-block RCE and exfiltration before Claude Code executes anything.
Big BrainSolve My Problem
humblejedi
302mo ago
Security●●Solid
Predicate-Claw – Run Time Assurance (RTA) for OpenClaw via Rust Sidecar
Transparent agent guardrail with <25ms latency, but agent security is early and fragmented.
WizardryNiche Gem
tonyww
213mo ago
Security●●Solid
Clawsec - Open-source plugin for OpenClaw that blocks dangerous actions
Every tool call is caught by middleware, scored against built-in rulesets like destructive-commands, secrets/* and exfiltration/* in under 5ms, then enforced as block/confirm/allow via a clawsec.yaml — neat, pragmatic attack surface reduction. The demo and auto-generated config make onboarding trivial, but it currently reads as an OpenClaw-first solution; broader agent-framework integrations or stronger isolation guarantees would make this a must-install.
Solve My ProblemNiche GemSlick
subho007
113mo ago
Security●●Solid
Aquaman keeping your OpenClaw secrets safe
The plugin-proxy split is smart: credentials live in a backend (Keychain/1Password/Vault/etc.) and a separate proxy injects auth headers over a UDS so the agent process never handles raw keys. It autosurveys plugin configs and channels to migrate plaintext secrets and even ships a Docker image and CLI for local setups — very practical for anyone already on OpenClaw, though it’s narrowly focused and adds an extra trusted component that deserves an audit.
Niche GemSolve My Problem
tech4242
104mo ago
Developer Tools●●Solid
Personal AI gateway for OpenClaw – tokenomics
OpenAI-compatible proxy with PII masking and token budgets—but LiteLLM, Helicone already do this.
Solve My ProblemBig Brain
crawdog
203mo ago