CLI appSecurity and privacy
Armorer-Guard
Block prompt injection, secret leaks, exfiltration, and risky tool calls locally.
- Stars
- 40
- Forks
- 10
- Updated
- Updated Jun 22, 2026
MIT
Block prompt injection, secret leaks, exfiltration, and risky tool calls locally.
Place the scanner between untrusted content, model output, and tool execution, or wrap a line-delimited stdio MCP server with its proxy. It detects prompt injection, credential disclosure, exfiltration, and destructive actions before forwarding a call, redacts secrets, and returns structured reasons for enforcement. The scanner makes no network calls and ships as a Rust CLI with Node and Python wrappers.
Resource types
Use cases
Runtime
Capabilities
Scan Agent Skills for injection, exfiltration, and malicious code patterns.
Connect to GlobalProtect VPNs on Linux through a CLI or GUI.
Public GitHub facts last synced Jul 10, 2026.
Scan Electron applications for insecure settings and implementation anti-patterns.
Scan agent skills with static checks, semantic review, and sandbox execution.