shellward
jnMetaCode/shellward
Agent security middleware with layered defenses: prompt injection detection, DLP data flow tracking, command blocking and PII detection.
- Local integrations
Installation, supported tools and required credentials are maintained by the project.
Project details
- GitHub stars
- 139
- Language
- TypeScript
- License
- Apache-2.0
- Forks
- 23
- Latest release
- v0.7.214mo ago
- Activity
- updated 23d ago
- Platforms listed
- macOS, Windows, Linux
- openclaw
- prompt-injection
- security
- ai-agent
- ai-security
- llm-security
- shellward
- pii-detection
First MCP server?Start with the basics
Scan code for security vulnerabilities using Semgrep.
IDA Pro plugin for binary analysis: decompilation, disassembly and automatic malware analysis reports.
Autonomous reverse engineering with Ghidra: decompile binaries, rename methods and data, and list methods, classes, imports and exports.
JADX decompiler plugin providing live, LLM-assisted reverse engineering.
Honeypot framework for building decoy MCP tools that an agent would never use in normal work, to detect prompt injection and malicious agent behavior.
Locally check npm and PyPI packages, such as those suggested by AI coding tools, for vulnerabilities and malicious code.
Dead code detection, security scanning and code quality analysis for Python, TypeScript and Go, with AI-assisted remediation.
Native Ghidra integration with GUI configuration, logging and no external dependencies.