Zero-dependency AST & heuristic bash command sandbox guard blocking destructive system mutations, path traversals, and reverse shells.
genpark-agent-bash-command-sandbox-guard-skill
Production-Grade Autonomous Agent Safety, Sandbox & Guardrail Skill • 100% Standard Library Python • Native Model Context Protocol (MCP)
genpark-agent-bash-command-sandbox-guard-skill provides zero-dependency, deterministic agentic execution safety, sandboxing, and financial circuit breakers engineered strictly using Python 3.9+ standard library.
🌟 Key Architectural Capabilities - Zero External Dependencies: Operates exclusively via pure Python (math, re, collections, heapq, hashlib, json). Zero pip install overhead, zero C-extension compile errors. - Enterprise Agent Safety Invariants: Implements formal defenses against destructive shell commands, prompt injections, runaway spend loops, differential privacy data leakage, and planning deadlocks. - Native Anthropic MCP Protocol: Compliant with standard JSON-RPC 2.0 stdio MCP specifications for Claude Desktop, Cursor, and Windsurf.
🔌 One-Click MCP Integration (Claude Desktop / Cursor)
Add to your claudedesktopconfig.json or cursor.json:
This skill contains pre-configured smithery.yaml and pyproject.toml manifests. Install directly via pip:
Maintained with ❤️ by GenPark AI Engineering • Powering Next-Gen Autonomous Cognitive Agents 🌍
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/alphaparkinc--genpark-agent-bash-command-sandbox-guard-skill.html)
Trajectory state entropy and cyclic repetition detector identifying autonomous agent infinite tool loops and planning deadlocks.
Alpha-Park/genpark-agent-prompt-injection-jailbreak-sentinel-skillMulti-vector heuristic prompt injection and jailbreak detector analyzing system overrides, delimiter breakouts, and base64 payload evasion.
alphaparkinc/genpark-agent-synthetic-data-differential-privacy-guard-skillDifferential privacy epsilon-noise generator and quasi-identifier redaction kernel protecting tabular data releases from re-identification.
Alpha-Park/genpark-agent-deadlock-liveloss-loop-detector-skillTrajectory state entropy and cyclic repetition detector identifying autonomous agent infinite tool loops and planning deadlocks.
alphaparkinc/genpark-agent-prompt-injection-jailbreak-sentinel-skillMulti-vector heuristic prompt injection and jailbreak detector analyzing system overrides, delimiter breakouts, and base64 payload evasion.
Alpha-Park/genpark-agent-bash-command-sandbox-guard-skillZero-dependency AST & heuristic bash command sandbox guard blocking destructive system mutations, path traversals, and reverse shells.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.