What AI says about llm-sast-scanner
The llm-sast-scanner is a general-purpose static application security testing (SAST) skill designed for use with LLM-based code agents (e.g., Claude Code, OpenAI Codex) to perform structured source-to-sink taint analysis across 34 vulnerability classes. It guides the AI through an evidence-based workflow: load vulnerability references, map sources, trace taint, verify findings with a Judge step, and report actionable results with file paths, line numbers, and remediation. It supports Java, Python, JavaScript/TypeScript, PHP, and .NET with language-specific detection rules, and can be installed by cloning the repository into the relevant AI agent's skills folder or downloaded manually.
AI named llm-sast-scanner from August 2026 to September 2026.
Questions and answers
- AI picks most
- We need to scan our code for insecure usage of LLM libraries. What's the best static analysis tool that understands AI security risks?AI picks Semgrep most
Excerpts where llm-sast-scanner appeared in the AI's answer
Google AI ModeAug 17, 2026, Google AI Mode Community projects like llm-sast-scanner provide specific AST and taint workflows focused explicitly on mapping dangerous multi-turn or agentic tool definitions
llm-sast-scanner in AI’s own words
Question: We need to scan our code for insecure usage of LLM libraries. What's the best static analysis tool that understands AI security risks?
Google AI ModeAug 17, 2026
Community projects like llm-sast-scanner provide specific AST and taint workflows focused explicitly on mapping dangerous multi-turn or agentic tool definitions
Google AI ModeAsk Google AI Mode yourself (opens in a new tab)ChatGPT SearchAsk ChatGPT yourself (opens in a new tab)
Competitors
CodeQL, NVIDIA Garak, and Semgrep appeared in every answer that named llm-sast-scanner.
Sources AI cites
AI cited github.com in these answers, after semgrep.dev.
github.com/sunweb3sec/llm-sast-scanner 13%Other sites 87%
