Skip to main content
skill CX Codex

sast-flow-tracer — Claude Code skill: what it does, how to install

The sast-flow-tracer skill maps paths from entry points to dangerous operations, following function calls, checks, and data transformations.

no license ★ 1,298 updated 2026-06-12

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add H-mmer/pentest-agents --skill sast-flow-tracer -a claude-code
Open on GitHub

What sast-flow-tracer does

sast-flow-tracer takes entries.json (where external data enters the code) and dangers.json (where potentially vulnerable operations execute), then determines for each pair whether the dangerous operation is reachable from the entry point. It walks the call graph, reads files across the project, expands macros, and records every validation and transformation — casts, assignments, field extractions. Outputs a JSON chain with a preliminary risk rating (hot, warm, cold).

Without Claude Opus, the reasoning depth is insufficient for cross-file tracing, and the skill will miss non-obvious paths. For PHP, it tracks extract(), unserialize(), magic methods, and Phar wrappers as second-order taint sources.

Runs via /sast command after other pipeline agents have populated entries.json and dangers.json.

What it helps with

  • map data flow graphs from user input to memory write operations
  • identify call chains where validation is missing or incomplete
  • track variable transformations through assignments and casts
  • recognize implicit entry points via $_SESSION, unserialize(), and Phar deserialization
  • record all bounds and type checks between entry and dangerous operation

Example prompts for the agent

  • Map data flows from entry points to dangerous operations in tcp_input.c
  • Check if $_POST['id'] reaches the unserialize() call in handlers/user.php
  • Track what validations exist between pkt->data and the memcpy() call on line 340

How to install sast-flow-tracer

1Skills CLI (Vercel)

npx skills add H-mmer/pentest-agents --skill sast-flow-tracer -a claude-code

2Manually: put the files in place

~/.claude/skills/agent-sast-flow-tracer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agent-sast-flow-tracer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about sast-flow-tracer

How to install sast-flow-tracer in Claude Code?

Run npx skills add H-mmer/pentest-agents --skill agent-sast-flow-tracer -a claude-code, then open ~/.claude/skills/agent-sast-flow-tracer/SKILL.md to verify.

What does sast-flow-tracer do?

It maps paths from entry points to dangerous operations: follows function calls, tracks variable transformations and checks, records each step, and rates the risk.

Why does sast-flow-tracer require Opus?

Cross-file tracing and understanding implicit dependencies through macros, extract(), and deserialization require deep reasoning available only in Claude Opus.

Similar skills

All skills for Security →

From the same set43

The whole set →
llm-ai-hunter llm-ai-hunter is a Claude Code skill that takes the role of an LLM and agentic AI security specialist. It covers OWASP LLM Top 10 v2025 and OWASP Agentic AI Top 10 across the full attack surface. CX Codex +1 ★ 1,298repo stars validator validator — a skill for vetting bug bounty findings before writing the report. Runs a 7-question system and 4-gate checklist, filters weak and theoretical bugs in minutes, and outputs a decision: PASS, KILL, DOWNGRADE, or CHAIN REQUIRED. CX Codex +1 ★ 1,298repo stars sast-flow-tracer sast-flow-tracer traces data propagation from attack entry points to dangerous operations and maps every validation step in between. CX Codex +1 ★ 1,298repo stars llm-ai-hunter llm-ai-hunter is a subagent that tests chatbots, RAG, MCP servers, and agent tools for security flaws within an authorized scope. CX Codex +1 ★ 1,298repo stars validator validator — a triage subagent for security researchers that kills weak findings before report writing using a 7-question gate and 4-gate validation checklist. Runs real HTTP proofs, not code review. CX Codex +1 ★ 1,298repo stars business-logic Guides coding assistants in auditing business logic flaws like price tampering, coupon race conditions, and MFA bypasses. Designed to prove impact for bug bounties. CX Codex +1 ★ 1,298repo stars browser-stealth-agent The browser-stealth-agent skill drives a local camofox-browser server to get past Cloudflare, Akamai, DataDome and PerimeterX bot checks, then verifies client-side bugs in a real browser. CX Codex +1 ★ 1,298repo stars sast-hunter The sast-hunter skill builds and runs a PoC for a specific suspected vulnerability. Use it after the candidate has passed code and condition checks. CX Codex +1 ★ 1,298repo stars

Project sponsors

Companies that keep this analytics open