715 tagged agent-security, measured the same way as everything else here.
Browse within: ai-security 24authorization 18llm-security 12oauth2 12zero-trust 12ai-governance 8AI Safety 7formal-verification 5
Plugin Claude Code
Runtime security for AI agents. Blocks destructive actions before execution, routes high-risk operations through human approval, and maintains an immutable audit trail. Covers OWASP MCP Top 10, ASI Top 10, and Agentic Skills Top 10.
Skill Claude CodeCodex
Use whenever security, policies, governance, guardrails, compliance, or safety are relevant — including blocked commands, audit trails, dangerous operations, deletions, file modifications, shell commands, MCP access, API calls, network requests, credentials, or any action that could be irreversible or destructive.
Skill Claude CodeCodex
Use this skill whenever security, policies, governance, guardrails, compliance, or safety are relevant — including blocked commands, audit trails, dangerous operations, deletions, file modifications, shell commands, MCP access, API calls, network requests, credentials, or any action that could be irreversible or…
Agent
Claude Code is Anthropic's CLI-based coding agent. ToolShield injects safety guidelines into its global instruction file.
Agent
Cursor is an AI-powered code editor. ToolShield injects safety guidelines into Cursor's global user rules stored in its internal SQLite database.
Agent
OpenHands is an open-source AI-driven development platform. ToolShield injects safety guidelines as a microagent that is always loaded into the agent's system prompt.
Agent-Threat-Rule/agent-threat-rules
Command Claude Code
Open GitHub issues on flagged repos to notify authors before public disclosure.
Agent-Threat-Rule/agent-threat-rules
Command Claude Code
Run incremental ecosystem scan: crawl registries → audit new packages → merge results → generate posts.
Agent-Threat-Rule/agent-threat-rules
Command Claude Code
Show current status of the scanning pipeline and content queue.
Agent-Threat-Rule/agent-threat-rules
Hook
Runs before the agent uses a tool, executing atr_scan.py via python3. From Agent-Threat-Rule/agent-threat-rules.
Skill Claude CodeCodex ✓ vendor
Call any REST API dynamically. Make GET, POST, PUT, DELETE requests to any endpoint with custom headers and JSON body.
Skill Claude CodeCodex ✓ vendor
Evaluate mathematical expressions and unit conversions. Handles arithmetic, percentages, exponents, and common unit conversions (temperature, distance, weight). No external dependencies.
Skill Claude CodeCodex ✓ vendor
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
Instructions file CodexOpenCode
Instructions for PrismorSec/prismor, covering agents.md, primary objectives, start here, how to work in this repo and 1. treat security guidance as product logic.
Instructions file
Instructions for PrismorSec/prismor, covering prismor security — claude.md, prismor runtime protection, cloaking (secret prevention) and working in this repo.
Skill Claude CodeCodex
Runtime security for AI coding agents. Use when about to install a package, paste a secret, run a destructive command, reach an unfamiliar host, govern MCP servers, set up a new workspace, or recover from a Prismor block.
Skill Claude CodeCodex
Verify a Beacon change end to end by running a real Claude Code session inside a disposable Linux cloud sandbox and checking that Beacon captured what the agent actually did. Use when asked to verify, validate, test, or prove that a Beacon change works for real rather than just compiling; when asked whether telemetry…
Instructions file CodexOpenCode
AGENTS.md instructions for Asymptote-Labs/agent-beacon, covering agent instructions for agent-beacon, verifying a change end to end and running the standard checks.
Instructions file
Claude Code instructions for Asymptote-Labs/agent-beacon, covering claude.md, project scope, product posture, telemetry scope and common commands.
Cursor rule Cursor
Cursor rule "cursorrules" from 0xNyk/awesome-agent-cortex, covering .cursorrules — cursor ide rules file, project context, tech stack, code style and development workflow.
Cursor rule
General coding conventions for all files.
Cursor rule
Testing conventions and patterns.
Agent Claude Code
Invoke ONLY when explicitly asked for an outside-in usability and adoption assessment of Caracal from a real external engineer's perspective. This agent evaluates: Console UX, SDK ergonomics, CLI experience, documentation clarity, deployment workflows, provider/gateway setup, policy model, app/resource modeling…
Agent Claude Code
Invoke ONLY when explicitly asked for a production-readiness audit or hardening of the Caracal OSS platform: reliability, stability, recoverability, scalability, observability, performance, operational simplicity, deployment, upgrade safety, and maintainability. Finds production gaps, explains root causes, designs…
At most 3 mods per repository are shown here — the rest are on their repository pages: