Proteus
Vyntra-Research/Proteus
Proteus is an assistant-oriented runtime and multi-agent skill suite designed for continuous vulnerability research and offensive codebase exploration. It provides structured local SQLite memory, validation gates, and specialist coordination to map codebases and construct non-obvious exploit chains.
29 4GPL-3.0Updated 2026-07-14
70
GoodOverview
Proteus serves as a comprehensive runtime environment and framework for autonomous vulnerability research, bug bounty operations, and security code audits. It combines persistent SQLite-backed target and global memory, integration with multiple assistant platforms (Codex, Claude Code, OpenCode), and specialized skills to help coordinators plan high-ROI research campaigns. The system emphasizes realistic attacker modeling, non-obvious multi-component chaining, negative controls, and rigorous validation gates to prevent false positives or weak hypotheses.
Capabilities
- ▸Continuous research campaign management with rounds, branches, and gates
- ▸SQLite-backed persistent target and global research memory
- ▸Non-obvious exploit chain hypothesis generation
- ▸Specialist front delegation for fuzzing, web intelligence, and PoC development
- ▸Validation gating against false positives and forced-vulnerable configurations
- ▸CLI and Model Context Protocol (MCP) server integration
Best for
Developing non-obvious, multi-component exploit chains from primitive behaviors and side effects., Managing continuous offensive security research campaigns across complex codebases with durable agent memory., Automating high-ROI security research planning, hypothesis generation, and specialist task delegation.
Works with
CodexClaude CodeOpenCode
Evoa Score breakdown= Σ (score × weight)
70Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%85 → +12.8
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%49 → +5.9
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%15 → +2.3
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%39 → +3.1
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%75 → +3.8
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total69.8 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Proteus is explicitly designed for offensive security research and vulnerability discovery. Deploying and using it requires proper authorization on target codebases to ensure compliance with legal and ethical standards.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.