Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jd-opensource/joysafeter/pentest-whitebox-code-reviewnpx skills add jd-opensource/JoySafeter --skill pentest-whitebox-code-reviewgit clone --depth 1 https://github.com/jd-opensource/JoySafeterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jd-opensource/joysafeter/pentest-whitebox-code-review)<a href="https://agentmods.dev/skills/jd-opensource/joysafeter/pentest-whitebox-code-review"><img src="https://agentmods.dev/badge/skills/jd-opensource/joysafeter/pentest-whitebox-code-review.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.01011 |
| Opus 5 | $0.00018 | $0.00505 |
| Sonnet 5 | $0.00007 | $0.00202 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
pentest-whitebox-code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pentest Whitebox Code Review
Purpose
Perform systematic white-box source code security audit using Shannon's backward taint analysis methodology. Traces from dangerous sinks back to user-controlled sources, classifies injection contexts by slot type, verifies XSS render contexts, and produces a prioritized exploitation queue for downstream proof-driven exploitation.
Prerequisites
Authorization Requirements
- Written authorization with explicit scope for source code review
- Source code access — full repository with version control history
- Architecture documentation if available (data flow diagrams, API specs)
- Deployment configuration access (environment variables, secrets management)
Environment Setup
- semgrep with custom rules for taint analysis
- CodeQL database built for target language
- ripgrep for fast pattern searching
- jadx for Android APK decompilation (if applicable)
- Source map extraction tools for minified JavaScript
- AST parsing tools for target language (tree-sitter, babel, etc.)
Core Workflow
Phase 1: Discovery
- Architecture Mapping: Identify application layers (routing, controllers, services, data access, templates). Map data flow from HTTP entry points through business logic to database/file/external sinks.
- Entry Point Enumeration: Catalog all user-controlled input sources — HTTP parameters, headers, cookies, file uploads, WebSocket messages, environment variables, database reads of user-stored data.
- Security Pattern Inventory: Identify existing security controls — input validation functions, output encoding helpers, parameterized query patterns, CSRF protections, authentication middleware, rate limiters.
Phase 2: Vulnerability Analysis (5 Parallel Tracks)
- Injection Sink Hunting: Backward taint from SQL/command/file/template sinks to sources. Classify each sink by slot type: SQL-val, SQL-ident, CMD-argument, FILE-path, TEMPLATE-expr. Verify whether parameterization or sanitization breaks the taint chain.
- XSS Render Context Analysis: Identify all dynamic output points in templates/responses. Classify each by render context: HTML_BODY, HTML_ATTRIBUTE, JAVASCRIPT_STRING, URL_PARAM, CSS_VALUE. Verify context-appropriate encoding is applied at each output point.
- Authentication Checklist (9-point): Transport security, rate limiting, session management, token properties, session fixation resistance, password policy enforcement, login response uniformity, account recovery security, SSO/OAuth implementation.
- Authorization Model Review (3-type): Horizontal (same-role cross-user access), vertical (privilege escalation across roles), context-workflow (state-dependent authorization bypass).
- SSRF Sink Hunting: Identify all outbound request sinks. Classify by type: classic (direct URL), blind (no response), semi-blind (partial response), stored (deferred execution). Trace URL construction from user input to request dispatch.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 77 lines · 36 tokens per session scan A 5aaf5194c302
pentest-whitebox-code-review is a skill published in the GitHub repository jd-opensource/JoySafeter (306 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,011 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
gossipcat
Use when installing or setting up gossipcat multi-agent orchestration (parallel review, consensus, adaptive dispatch) in Claude Code or Cursor. Installs the gossipcat MCP server and hands off to gossipstatus() for all live rules.
swarmclaw
AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
codex-judge
Cross-provider LLM judge using Codex (GPT-5) to evaluate implementations written by Claude. Internal skill invoked by the insistir lead during the review loop. Not user-facing.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
skill-creator
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating…