kernora-ai

kernora-ai/agent-sec

Plugin Claude Code

Plugin marketplace listing 1 plugin: kernora-agent-security.

kernora-ai/agent-sec

Plugin Claude Code

Grounds your AI coding agent in a cited security baseline (OWASP/CWE/EU AI Act) and warns before risky actions. Advisory, free, read-only. Real-time blocking is Kernora Axiora.

kernora-ai/agent-sec

Command

Ask Kernora Agent Security whether an action is risky. Usage — /agentsec-check.

kernora-ai/agent-sec

Command

Local effectiveness report — how many actions Kernora Agent Security flagged in your own sessions (read from /.agentsec/flags.log; nothing is sent anywhere).

kernora-ai/agent-sec

Command

Show the full Kernora Agent Security baseline — every rule served by the agentsec MCP, with its severity and cited source (OWASP/CWE/EU AI Act).

kernora-ai/agent-sec

Hook

Runs before the agent uses a tool for Bash tool calls, executing check_action.py. From kernora-ai/agent-sec.

kernora-ai/agent-sec

Skill Claude CodeCodex

Use BEFORE running a shell command or writing code that handles secrets/keys, deletes files, adds a dependency, weakens auth or TLS, force-pushes, or makes an outbound network call. Consults the Kernora Agent Security baseline (cited OWASP/CWE/EU-AI-Act rules) so the agent self-corrects.

kernora-ai/agent-sec

MCP server Claude CodeCodexCursor

Zero-install security baseline for AI coding agents — OWASP/CWE-cited rules over MCP. Remote server at agentsec.kernora.ai.