CS292C
fredfeng/CS292C
This repository contains course materials for a graduate seminar at UC Santa Barbara on formal methods for agentic programming and AI agent security.
29 14No licenseUpdated 2026-05-24
65
GoodOverview
CS292C explores the intersection of formal methods, verification, and autonomous AI coding agents. The curriculum covers agent foundations, model context protocol (MCP), Hoare logic, SAT/SMT solvers, static analysis, threat landscapes, skill supply-chain security, fuzzing, and runtime guardrails, preparing students to verify and harden agentic systems.
Capabilities
- ▸Formal verification using Z3 and Hoare logic
- ▸Static analysis and taint tracking for skill auditing
- ▸Fuzzing and behavioral testing for agentic systems
- ▸Model Context Protocol (MCP) and tool-use integration
Best for
Studying graduate-level coursework on AI agent verification and safety, Learning formal methods like Hoare logic and SMT solvers applied to LLM agents, Auditing and securing agent skills against supply-chain attacks and prompt injection, Implementing runtime guardrails and token optimization for production AI agents
Works with
Claude CodeCursorCodex
Evoa Score breakdown= Σ (score × weight)
65Task usefulness20%77 → +15.4
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%85 → +12.8
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%31 → +3.7
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%100 → +15.0
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%95 → +9.5
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%44 → +3.5
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 total76.4 / 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
The course specifically teaches about the security threat landscape of agentic systems, including prompt injection, credential exfiltration, and tool poisoning, providing defensive frameworks and auditing skills.
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.