81 tagged ai security tool, measured the same way as everything else here.
Browse within: Autonomous Agents 50multi-agent-systems 50offensive-security 50ai-cybersecurity 16ai-penetration-testing 16ctf-tools 16ai-security 15appsec 5ctfs 5
Agent
A planning agent for authorized, non-destructive security testing. It creates and revises detailed steps for an executor agent, with each step stating the target, allowed scope, one action, and expected evidence.
Agent
A supervisor agent that coordinates specialist agents by sending each one a defined part of a task. It handles simple tasks itself and combines specialist work when broader coordination is needed.
Agent
Instructions for a coordinating agent that plans multi-agent security work, delegates separate tasks, combines evidence, and delivers the result. A multi-agent workflow uses several specialized agents on parts of one job.
Agent
Fully autonomous pentest sub agent using MCP-backed Darkmoon toolbox for Drupal applications (core, contrib modules, JSON:API, REST, Entity/Field system, Render API, Twig, Views, Drupal Commerce, roles/permissions).
Agent
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for web application navigation with headless browser.
Agent
Fully autonomous pentest sub agent using MCP-backed Darkmoon toolbox for Moodle LMS applications (core, plugins, Web Services API, quiz/grade/enrollment logic, scheduled tasks, roles/capabilities).
Agent
Version: 0.1.0-draft Scope: Architectural decisions, trade-off analysis, and ADR authoring for tooling and infrastructure changes in the secure-ai-tooling repository.
Agent
Version: 0.3.0-draft Scope: Content update review for the CoSAI Risk Map framework (secure-ai-tooling repository).
Agent
Version: 0.1.0-draft Scope: Generate structured review comments for GitHub issues proposing new or updated content in the CoSAI Risk Map framework (secure-ai-tooling repository).
Agent Claude Code
SafeClaw tracks OpenClaw AI agent activities using a dual-source approach because the gateway WebSocket does NOT broadcast tool call events.
Agent Claude Code
You are a specialist agent for publishing the safeclaw npm package. Follow these instructions exactly.
Agent Claude Code
The Skill Scanner provides proactive, pre-execution security analysis of markdown skill definitions. While SafeClaw's runtime Threat Analysis Engine (TC- categories) classifies activities as they happen, the Skill Scanner inspects skill files before\ they're loaded — catching hidden threats that are invisible to human…
Agent
Subdomain enumeration and live host discovery specialist. Runs Chaos API (ProjectDiscovery), subfinder, assetfinder, dnsx, httpx, katana, waybackurls, gau, and nuclei. Produces prioritized attack surface for a target. Use when starting recon on a new target domain.
Agent
Bug bounty report writer. Generates professional H1/Bugcrowd/Intigriti/Immunefi reports. Impact-first writing, human tone, no theoretical language, CVSS 3.1 calculation included. Use after a finding has passed the 7-Question Gate and 4 validation gates. Never generates reports with "could potentially" language.
Agent
Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…