Back to directory

Chain Hunter

Agent skill
1 skill

Multi-step attack chain constructor. Ingests chain-flagged TrafficTriage findings and SourceHunter correlations to build exploit chains where individual vulnerabilities are insufficient on their own but combine for high-impact compound exploitation paths (e.g., SSRF → IMDS → privilege escalation, or open-redirect → OAuth code theft → account takeover). Uses a hybrid neuro-symbolic pipeline: LLM extracts structured capability requires/grants per finding, a bounded graph search enumerates paths, and a novelty scorer (embedding cosine distance from KG priors) prioritizes genuinely new attack patterns. Emits Mermaid attack-path diagrams alongside structured JSON and Markdown PoC artifacts.

Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI

Supported by the Atlas install prompt. Skill-specific requirements vary.

Skill stats

Skills1CategorySecurityStars0

About this skill

Multi-step attack chain constructor. Ingests chain-flagged TrafficTriage findings and SourceHunter correlations to build exploit chains where individual vulnerabilities are insufficient on their own but combine for high-impact compound exploitation paths (e.g., SSRF → IMDS → privilege escalation, or open-redirect → OAuth code theft → account takeover). Uses a hybrid neuro-symbolic pipeline: LLM extracts structured capability requires/grants per finding, a bounded graph search enumerates paths, and a novelty scorer (embedding cosine distance from KG priors) prioritizes genuinely new attack patterns. Emits Mermaid attack-path diagrams alongside structured JSON and Markdown PoC artifacts.

Quick start

  1. Copy the install prompt. Use the green button above this README.
  2. Send it to your agent. Paste it into your coding agent’s chat and send.
  3. Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
Review the source before using this skill

This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.

Automated security scan: Partial

Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.

0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1

Content SHA-256: 5854c7c516635f524efd1e071d71700798fc89571aba128895802e783b791d7e

About scan coverage and limitations

About this listing

Category
Security
Reported license
Not specified
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.