# sast-hunter

sast-hunter validates candidate vulnerabilities from static analysis. Builds minimal test cases and runs them under sanitizers like ASan to confirm bugs or reject false alarms.

- subagent · `type=agent` · Claude Code, Cursor, Codex, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop) · ★ 1298 repo stars
- Author: H-mmer
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/H-mmer/pentest-agents/tree/HEAD/.claude/agents/sast-hunter.md
- Updated: 2026-06-12
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/sast-hunter

## What it does

The subagent processes candidate flaws that passed initial filtering. Instead of broad code audits, it focuses on verifying a single data path between an entry point and an unsafe operation.

It writes a minimal test harness and executes target binaries with AddressSanitizer or Valgrind. When memory corruption or runtime exceptions occur during execution, the finding gets verified.

Configuration specifies MCP tools from `writeup-search` to query technique references, but testing proceeds even when MCP is offline. Verifying native C or C++ issues requires a local compiler configured with sanitizer flags.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/sast-hunter.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/sast-hunter.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/sast-hunter.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/H-mmer/pentest-agents/tree/HEAD/.claude/agents/sast-hunter.md

## When to use it
- verify static analysis warnings using memory sanitizers
- eliminate false positive vulnerability reports
- write minimal test harnesses to reproduce reported crashes
- inspect edge cases in unvalidated code paths

## Example prompts
- Run sast-hunter on candidate issue 12 using ASan build flags
- /sast verify the memory corruption hypothesis in parser.c
- Build a minimal test case for the unvalidated buffer in network handler

## Similar
- [sast-configuration](https://affpapa.org/en/nevibecode/skills/sast-configuration.md) — skill · 10800 installs
- [sast-scanning](https://affpapa.org/en/nevibecode/skills/sast-scanning.md) — skill · 415 installs
- [security-scanning-security-sast](https://affpapa.org/en/nevibecode/skills/security-scanning-security-sast.md) — skill · ★ 50109 repo stars
- [security-sast](https://affpapa.org/en/nevibecode/commands/security-sast.md) — command · ★ 42780 repo stars
- [sast-sca-security-analyzer](https://affpapa.org/en/nevibecode/agents/sast-sca-security-analyzer.md) — subagent · ★ 41430 repo stars
- [LucidShark](https://affpapa.org/en/nevibecode/mcp/lucidshark.md) — MCP server · ★ 20 repo stars

From the same set: [h-mmer/pentest-agents](https://affpapa.org/en/nevibecode/by/h-mmer/pentest-agents.md) — 43 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
