Compiler-style pre-execution safety analysis for Harness shell actions.
Pi guardrails that keep LLM shell and file access safe, transparent, and user-approved.
Structured policy decisions for AI-generated shell commands and filesystem paths.
Bounded shell and CLI execution for AI agents: structured contracts, policy-gated execution, hardened Linux runtime enforcement, and signed receipts.
Shellsafe - Trust Layer for AI Agent Skills
Semantic paste firewall for Linux terminals that warns before risky copied shell commands run.
Windows safety layer for AI coding agents, protecting Git worktrees and important folders from destructive shell commands.
Defense-in-depth against curl|bash attacks. Four-layer shell interception (accept-line, ZLE paste, hardened wrappers, preexec audit) with YARA-based detection. Catches malicious piped installs before execution — where macOS Gatekeeper can't.
Security skills for Minis on iOS: agent operational safety and prompt-injection defense.
AI-powered shell command interceptor built with Rust. Analyzes command intent via Gemini API and provides risk-based control (Pass/Warning/Block) in real-time.
To associate your repository with the shell-security topic, visit your repo's landing page and select "manage topics."