Skip to content

sekar3s/secure-code-guardian

v1.1.0MIT

Security guardrails for AI agents: blocks destructive commands and secret access with hooks, scans for secrets and vulnerable dependencies (OSV.dev) via MCP, and adds a security-reviewer agent and threat-model skill.

GitHubOpen Website
threat-model

Produce a lightweight STRIDE threat model for an application, service or feature — data-flow diagram (Mermaid), trust boundaries, threats with risk ratings and concrete mitigations. Use when asked for a threat model, security design review, attack surface analysis, or "what could go wrong" for a system or change.