Agent skill · security · aradotso
awesome-ai-security-tools-guide
Navigate and recommend tools from the curated Awesome AI Security Tools list covering autotriage, agent security, AI/ML supply chain, pentest agents, LLM red-teaming, and more.
Why this skill is useful
Provides a curated list of niche AI security tools and frameworks that the AI wouldn't reliably generate on its own.
What it needs
About 6k tokens when loaded. Last updated 2026-08-04. 11 stars on the source repository.
What this skill does
awesome-ai-security-tools-guide Skill by ara.so — Security Skills collection. This skill provides expertise in navigating and recommending tools from the Awesome AI Security Tools curated list. The repository organizes public-source, research, and commercial tools across 15+ categories: autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven fuzzing, threat intelligence, SOC/SIEM triage, reverse engineering, and LLM red-teaming. Overview The list uses a type legend: 🟢 public source / open-source 🔬 research (paper / benchmark / dataset / framework) 🟠 commercial with open components ⚠️ restrictive, non-commercial, or unclear/no license Each entry includes GitHub stars, last-commit badges, and related/alternative tools. Installation The repository itself is a curated list (README.md) — no installation required. Clone for offline reference: Or browse online at: Key Categories 1. Autotriage of Security Findings Tools that use LLMs to triage, deduplicate, and validate scanner output. Top picks: nuclei-autotriage — Two-stage LLM triage (falsifier + red-team pass) for Nuclei JSONL findings seclab-taskflow-agent — YAML-driven taskflow for CodeQL/SAST false-positive filtering (GitHub Security Lab) honeyslop — Code-canary decoys to detect AI-hallucinated vulnerability reports Example use case: 2. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/awesome-ai-security-tools-guide