agent security plugins

charliechenye/SkillGate

Plugin Claude Code

Reduced plugin manifest for fixture coverage.

William2333ZZ/trustshell

Plugin Claude Code

Plugin marketplace listing 1 plugin: trustshell.

William2333ZZ/trustshell

Plugin Claude Code

AI agent security for Claude Code — read the code, break the running agent, prove it (exploit-validated). Commands: /static-scan, /red-team. Subagent: agent-red-teamer. Skills: RT-1..RT-9.

ilyautov/cordon

Plugin Claude Code

Plugin marketplace listing 1 plugin: cordon.

ilyautov/cordon

Plugin Claude Code

Deterministic layer between untrusted content and agent actions.

stefans71/telekey-mcp

Plugin Claude Code

Plugin marketplace listing 1 plugin: telekey.

stefans71/telekey-mcp

Plugin Claude Code

Give each agent a key scoped to one job that can only narrow, never widen. A prompt-injected agent reaches for a capability it was never given — the call is blocked before it runs. Enforced on every tool call via a PreToolUse hook.

mlawsonking/MCP

Plugin Claude Code

Deterministic security checks for coding agents, from the repo that publishes the six agent-guards MCP servers.

mlawsonking/MCP

Plugin Claude Code

Deterministic security checks in Claude Code's path: package names before an install, secrets and code rules on what was just written, injection and Unicode-obfuscation patterns in fetched pages. No network call in any hook, no model in any check.