agent-security plugins

Asymptote-Labs/agent-beacon

Plugin Claude Code

Bundles 5 skills, 1 MCP server · 515 tokens together

Cross-harness memory from Beacon traces: recall reviewed project lessons, distill agent sessions into approved memory, promote memory to Agent Skills, build dashboard lenses, and share sessions to beacon.sh.

hashgraph-online/hol-guard

Plugin Claude Code

Bundles 2 skills · 67 tokens together

Install and manage the local-first HOL Guard package for Claude Code. This plugin guides setup and status checks; HOL Guard itself installs and owns runtime security hooks for risky commands, secrets, packages, MCP, and supply-chain activity.

emiliaprotocol/emilia-protocol

Plugin Claude Code

Bundles 1 hook

Require a named human's signed approval before Claude does anything irreversible — money movement, destructive shell, external sends. High-risk tool calls are held until a person approves on their own device (Face ID / passkey), producing an offline-verifiable Trust Receipt. Fail-closed.

secureagentics/Adrian

Plugin Claude Code

Bundles 2 commands, 7 hooks · 29 tokens together

Adrian runtime security: observability and blocking for Claude Code sessions.

SponsioLabs/Sponsio

Plugin Claude Code

Bundles 1 skill, 1 hook · 263 tokens together

Runtime contract guardrails for every tool call in your Claude Code session — backed by per-plugin contract libraries under /.sponsio/plugins/.

pegasi-ai/reins

Plugin Claude Code

Bundles 1 skill, 2 hooks, 1 plugin · 90 tokens together

Security controls for AI agents — deterministic policy enforcement, OWASP ASI10 scanning, and audit trails.

OraclesTech/guardian-sdk

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 78 tokens together

Runtime AI-threat screening for Claude: analyze prompts, scan tool calls and outputs, and vet documents before you act, with BLOCK / CHALLENGE / ALLOW verdicts. Paid feature — needs a Pro-plan-or-higher Guardian API key.

open-agent-ai-security/praxen

Plugin Claude Code

Bundles 1 skill · 184 tokens together

Praxen — agent behavior verifier. Compares an AI agent's declared policy (Worker Remit) against the available evidence — source code, live deployment state, or behavioral artifacts — and reports where observed behavior diverges from declared intent. Make sure your agent does its job — and only its job.

christopherkarani/ryk

Plugin Claude Code

Bundles 5 skills · 0 tokens together

ryk safety hooks and skills for Claude Code.

Prismer-AI/signet

Plugin Claude Code

Bundles 1 skill, 1 hook · 16 tokens together

Cryptographic signing for every AI agent tool call — Ed25519 receipts + hash-chained audit log.

GeckoVision/gecko-surf

Plugin Claude Code

Bundles 6 skills, 2 commands, 2 agents · 1,131 tokens together

Make any API agent-usable — even one with broken docs, no OpenAPI, a WAF, or an auth wall. Comprehend a spec (or JS-rendered docs) into first-call-correct MCP tools your agent calls right the first time, with auth injected and no integration code. On a painful real API, first-call-correctness goes from 10% to 65%…

vaaraio/vaara

Plugin Claude Code

Bundles 2 commands, 4 hooks · 48 tokens together

Accountable autonomy for Claude Code. PreToolUse runs a two-layer check on Bash, WebFetch, WebSearch, Write, Edit, NotebookEdit, Task, SendMessage and MCP calls (regex deny patterns on shell, web and file mutation; conformal risk scorer on MCP). PostToolUse writes a hash-chained SQLite audit record across the same set.

taoq-ai/ziran

Plugin Claude Code

Bundles 1 MCP server

safe-plugin. ZIRAN finds the vulnerabilities in AI agents that come from tools combining, not from any single prompt. Graph-based tool chain discovery, execution-level side-effect detection, multi-phase campaigns.

sunglasses-dev/sunglasses

Plugin Claude Code

Bundles 1 MCP server

Local input firewall for AI agents. Scans text and files before an agent reads them. Needs pip install sunglasses first, on Python 3.9 or newer.

cylestio/agent-inspector

Plugin Claude Code

Bundles 9 commands · 478 tokens together

AI Agent Security Analysis - scan, fix, analyze, and report on AI agent vulnerabilities using OWASP LLM Top 10.

ilyautov/cordon

Plugin Gemini CLI

A prompt-injection firewall for AI agents, with no AI inside: your agent reads anything and takes orders only from you. For Claude Code, Codex CLI, Kimi Code, DeepSeek Harness, Gemini CLI, MCP hosts and LangChain.

Synapsor/Synapsor-Runner

Plugin Cursor

Bundles 1 skill, 1 command · 53 tokens together

Turn one application data change into a disabled, reviewable Synapsor Safe Action without giving the Cursor agent SQL or commit authority.

William2333ZZ/trustshell

Plugin Claude Code

Bundles 12 skills, 2 commands, 1 agent · 932 tokens together

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.

mlawsonking/MCP

Plugin Claude Code

Bundles 1 skill, 2 hooks · 72 tokens together

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.

jdhart81/viridis-agent-fleet

Plugin Claude Code

Bundles 1 skill, 1 MCP server · 37 tokens together

Evidence-bounded diagnostics with SecurityPreflight MCP discovery and public receipts.