tool · first seen 15 Oct 2026
static application security testing
Also: SAST
Analyzing source code without executing it to detect security vulnerabilities.
Static application security testing (SAST) analyzes source code without running it to find vulnerabilities, and it has been a standard part of application security practice for many years. The recent sources are mostly evaluations and extensions of existing tools. One paper benchmarks CodeQL, Infer and Semgrep across a decade of C/C++ code, another studies SAST on Rust, and a third tests SAST across languages using EV charging protocol implementations. Several papers pair SAST with LLMs to triage, explain or test its findings, among them Snyk's VulnBench comparison with AI security agents. Small GitHub tools package SAST as Claude Code plugins or MCP servers for AI-generated apps.
The idea itself is not new. The active thread is how deterministic SAST is being combined with LLM agents, where the static analyzer stays authoritative for detection and the model handles triage, explanation and coverage gaps.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 53 on 14 Nov 2026 · 7 mentions in 28 days · 7 independent groups · papers → code · first seen 4 weeks ago · acceleration +0.98
Earliest sources
- Combining LLM and Dynamic Analysis for Universal Testing of Static Application Security Testing ToolsPapers · 15 Oct 2026 · Huaien Zhang, Yu Pei, Hao Chen, Shin Hwei Tan
- Evaluating and Improving Static Application Security Testing Tools for RustPapers · 15 Oct 2026 · Huaien Zhang, Zhengjie Zhao, Yu Pei, Tian Dong, Minxue Pan, Shin Hwei Tan, Hao C…
- VulnSAGE: Adjudicating SAST Reports by Connecting LLM Reasoning to Program StructurePapers · 16 Oct 2026 · Jinbao Chen, Zixiang Zhou, Yu Zhang, Yihong Wu
- ratomirjovanovic/pandawardCode · 27 Oct 2026 · ratomirjovanovic · 50 stars
- How Deterministic SAST and AI Security Agents Divide the Work: Coverage, Harness Policy and Cost in Snyk VulnBench 2.0Papers · 28 Oct 2026 · Liran Tal, Chris Liu, Charlotte Fereday, Sebastian Roth, Brian Clark
- Fixed Detectors, Moving Code: How Well Do Static Security Analyzers Hold Up over a Decade of C/C++ Evolution?Papers · 2 Nov 2026 · Junhua Tang, Zhengsong Zhang. Haipeng Cai
Latest sources
- How Well Do SAST Tools Work Across Languages? An Empirical Study Using OCPP ImplementationsPapers · 10 Nov 2026 · Zachary Wadhams, Emma Sheppard, Dalton Arford, Clemente Izurieta, Ann Marie Rein…
- Code-Grounded Agentic Explanations for Static Analysis Vulnerability FindingsPapers · 9 Nov 2026 · Oshando Johnson, Ranjith Krishnamurthy, Rohith Kumar Shanmuganathan, Goran Piska…
- avivgerz-hue/vibe-shieldCode · 7 Nov 2026 · avivgerz-hue · 45 stars
- Governed Self-Improvement for a Local-First Security Analyzer: Baseline Measurements and a Preregistered Evaluation Protocol for Tantular CyberPapers · 7 Nov 2026 · Raditio Ghifiardi, Rifny Rachman
- Fixed Detectors, Moving Code: How Well Do Static Security Analyzers Hold Up over a Decade of C/C++ Evolution?Papers · 2 Nov 2026 · Junhua Tang, Zhengsong Zhang. Haipeng Cai
- How Deterministic SAST and AI Security Agents Divide the Work: Coverage, Harness Policy and Cost in Snyk VulnBench 2.0Papers · 28 Oct 2026 · Liran Tal, Chris Liu, Charlotte Fereday, Sebastian Roth, Brian Clark
- ratomirjovanovic/pandawardCode · 27 Oct 2026 · ratomirjovanovic · 50 stars
- VulnSAGE: Adjudicating SAST Reports by Connecting LLM Reasoning to Program StructurePapers · 16 Oct 2026 · Jinbao Chen, Zixiang Zhou, Yu Zhang, Yihong Wu
- Evaluating and Improving Static Application Security Testing Tools for RustPapers · 15 Oct 2026 · Huaien Zhang, Zhengjie Zhao, Yu Pei, Tian Dong, Minxue Pan, Shin Hwei Tan, Hao C…
- Combining LLM and Dynamic Analysis for Universal Testing of Static Application Security Testing ToolsPapers · 15 Oct 2026 · Huaien Zhang, Yu Pei, Hao Chen, Shin Hwei Tan