dreadnode/capabilities

Dreadnode 기능

이것은 Dreadnode가 app.dreadnode.io에 게시하는 기능에 대한 소스 저장소입니다. 이 기능은 디렉토리입니다. 에이전트, 도구, 기술 및 MCP 서버의 모든 조합과는 동일합니다. Dreadnode runtime 픽업 및로드 :

설치

-Published — dn capability install dreadnode/ai-red-teaming ([T1]])

• 소스에서 - dn capability install ./capabilities/ai-red-teaming symlinks 디렉토리를 실행 시간으로, 그래서 다시로드에 살고 편집
• TUI - start dn, press Ctrl+P], dreadnode/] 필터

dn는 Dreadnode CLI - 설치 및 인증에 얻은 것을 볼 수 있습니다. docs.dreadnode.io/capabilities/installing에서 기능에 대한 전체 설치 참조.

자신의 빌드

capabilities/의 각 디렉토리는 배송, 작업 예입니다. docs와 함께 하나 읽기 :

• 컨셉 및 로드 모델
• Manifest 참고
• Quickstart - 대략 10 분에 TUI에서 실행하는 비계

보안 검사

이 repo에 있는 각 기술은 신속한 주입, 자료 exfiltration, 공구 사슬 남용 및 공급 사슬 위험을 위한 NVIDIA SkillSpector로 검사됩니다.

Dreadnode Capabilities

This is the source repo for the capabilities Dreadnode publishes to app.dreadnode.io. A capability is a directory — a manifest plus any combination of agents, tools, skills, and MCP servers — that a Dreadnode runtime picks up and loads:

ai-red-teaming/
  capability.yaml     # manifest
  agents/             # markdown prompts
  tools/              # python @tool functions
  skills/             # SKILL.md packs

Install one

• Published — dn capability install dreadnode/ai-red-teaming (swap in any name from capabilities/)
• From source — dn capability install ./capabilities/ai-red-teaming symlinks the directory into your runtime, so edits go live on reload
• From the TUI — start dn, press Ctrl+P, filter for dreadnode/

dn is the Dreadnode CLI — see getting-started to install and authenticate. Full install reference for capabilities lives at docs.dreadnode.io/capabilities/installing.

Build your own

Every directory under capabilities/ is a shipped, working example. Read one alongside the docs:

• Concepts and load model
• Manifest reference
• Quickstart — scaffold to running in the TUI in about ten minutes

Security scanning

Every skill in this repo is scanned with NVIDIA SkillSpector for prompt injection, data exfiltration, tool-chaining abuse, and supply chain risk. CI runs SkillSpector in static mode (--no-llm) for deterministic scans without provider API keys, uploads SARIF reports to GitHub Code Scanning, and reports findings. Because security-focused capabilities intentionally contain offensive security content, the workflow currently reports findings without blocking merges while thresholds are tuned.

just security-scan                    # scan all capabilities
just security-scan web-security       # scan one capability
just security-scan behavioral="true"  # ignored by SkillSpector; kept for compatibility