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 skills add eugenepyvovarov/mcpbundler-agent-skills-marketplace --skill vulnhuntergit clone --depth 1 https://github.com/eugenepyvovarov/mcpbundler-agent-skills-marketplaceWrote 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/eugenepyvovarov/mcpbundler-agent-skills-marketplace/vulnhunter)<a href="https://agentmods.dev/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/vulnhunter"><img src="https://agentmods.dev/badge/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/vulnhunter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/vulnhunter"><img src="https://agentmods.dev/badge/skills/eugenepyvovarov/mcpbundler-agent-skills-marketplace/vulnhunter.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.02019 |
| Opus 5 | $0.00000 | $0.01009 |
| Sonnet 5 | $0.00000 | $0.00404 |
| Haiku 4.5 | $0.00000 | $0.00202 |
Grade A, and why
vulnhunter scanned grade A with 1 finding 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
os.system(), subprocess with shell=True This is a copy
88% identical to vulnhunter — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VulnHunter - Security Vulnerability Detection & Analysis
A comprehensive security audit skill for identifying dangerous APIs, footgun patterns, error-prone configurations, and hunting for vulnerability variants across codebases. Inspired by Trail of Bits' sharp-edges and variant-analysis methodologies.
Overview
VulnHunter combines two powerful security analysis techniques:
- Sharp Edges Detection - Identify error-prone APIs, dangerous defaults, and footgun designs
- Variant Analysis - Find similar vulnerabilities across codebases using pattern-based analysis
When to Use VulnHunter
Activate this skill when:
- Conducting security code reviews or audits
- Reviewing third-party dependencies for dangerous patterns
- Hunting for variants of known vulnerabilities
- Assessing API design for security footguns
- Pre-audit reconnaissance of unfamiliar codebases
Sharp Edges Detection
Categories of Sharp Edges
1. Dangerous Default Configurations
Look for configurations that are insecure by default:
- CORS: Access-Control-Allow-Origin: *
- Debug modes enabled in production
- Default credentials or API keys
- Permissive file permissions (777, 666)
- SSL/TLS verification disabled
- Insecure deserialization settings
2. Error-Prone APIs
Memory Safety:
// Dangerous: No bounds checking
strcpy(), strcat(), sprintf(), gets()
memcpy() without size validation
// Safer alternatives
strncpy(), strncat(), snprintf(), fgets()
memcpy_s() with explicit size
Cryptography Footguns:
- ECB mode encryption
- MD5/SHA1 for security purposes
- Hardcoded IVs or salts
- Custom crypto implementations
- Random without CSPRNG (Math.random for tokens)
Concurrency Issues:
- Race conditions in file operations
- Time-of-check to time-of-use (TOCTOU)
- Double-checked locking anti-patterns
- Non-atomic increment/decrement operations
3. Language-Specific Footguns
JavaScript/TypeScript:
// Dangerous patterns
eval(), new Function(), setTimeout(string)
innerHTML, outerHTML, document.write()
Object.assign() for deep clone (shallow only!)
== instead of === (type coercion)
What ships with it
6 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.
- 9d ago First seen · 303 lines · 0 tokens per session scan A 191310cb13e9
vulnhunter is a skill published in the GitHub repository eugenepyvovarov/mcpbundler-agent-skills-marketplace (12 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,019 tokens. A static security scan graded it A with 1 finding (runs shell commands). It is 88% identical to vulnhunter, differing in 5 lines, and is treated as a copy.
Other skills, from other repositories
agent-watchdog
Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently investigate the same…
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.
baocut
BaoCut-only operator for the installed bcut CLI and .bcut projects. Implicitly trigger only when the request explicitly names BaoCut or bcut, targets a .bcut project or BaoCut Subtitle Studio, or continues a BaoCut workflow already established in the conversation. Do not trigger solely for generic audio or video…
graphify-dotnet
Use graphify-dotnet to generate codebase knowledge graphs, architecture snapshots, and exportable repository maps from .NET or polyglot source trees, with optional AI-enriched semantic relationships. USE FOR: graphify commands; graph JSON, HTML, SVG, Cypher, Markdown, and Obsidian exports; repository map and…
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".