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/pekral/cursor-rules/security-bounty-hunternpx skills add pekral/cursor-rules --skill security-bounty-huntergit clone --depth 1 https://github.com/pekral/cursor-rulesWrote 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/pekral/cursor-rules/security-bounty-hunter)<a href="https://agentmods.dev/skills/pekral/cursor-rules/security-bounty-hunter"><img src="https://agentmods.dev/badge/skills/pekral/cursor-rules/security-bounty-hunter.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 | $0.00058 | $0.01561 |
| Opus 5 | $0.00029 | $0.00781 |
| Sonnet 5 | $0.00012 | $0.00312 |
| Haiku 4.5 | $0.00006 | $0.00156 |
Grade A, and why
security-bounty-hunter 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 2d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Bounty Hunter
Constraints
- Apply
@rules/security/backend.mdand@rules/security/frontend.md - If the project uses Laravel, also apply
@rules/laravel/laravel.mdc - Stack assumed: Laravel 11 / PHP 8.3, Filament, Livewire, Alpine.js, Blade, MySQL, Redis
- Read-only investigation — never modify, stage, commit, or push code; output is the finding report only
- Never run an exploit against infrastructure you are not authorized to test; keep PoCs minimal and safe
- Hard limits: this file stays <= 500 lines and <= 5000 tokens
Purpose
Find unknown, exploitable bugs reachable from a real network or user boundary, and write them up to a standard a bounty program will accept. Bias toward "does this actually pay?" over "is this theoretically unsafe?".
How this differs from neighbors:
@skills/security-review/SKILL.mdreviews a diff against best practices; this skill hunts unknown exploitable bugs across the whole reachable surface.@skills/security-threat-analysis/SKILL.mdremediates a known advisory/CVE; this skill discovers the unknown one.
Use when
- Sweeping a repository for exploitable vulnerabilities
- Preparing a Huntr / HackerOne / program submission
- Triage where the question is "is this reportable?" not "is this tidy?"
In-Scope Patterns (mapped to PHP/Laravel sinks)
| Pattern | CWE | PHP/Laravel sink to chase | Impact |
|---|---|---|---|
| SSRF via user-controlled URL | CWE-918 | Http::get($userUrl), Guzzle, file_get_contents($userUrl) |
internal network / cloud metadata |
| SQL injection | CWE-89 | whereRaw/orderByRaw/havingRaw/DB::statement/DB::raw with interpolation |
data exfiltration, auth bypass |
| Auth / access bypass | CWE-287/639 | gaps in middleware, policy/gate, Livewire actions, IDOR on route-model binding | unauthorized data access |
| Unsafe deserialization | CWE-502 | unserialize($userInput), unsigned cookie/cache payloads, ShouldQueue from untrusted source |
RCE / object injection |
| Path traversal | CWE-22 | Storage::get/disk()->get, file_get_contents, download routes with ../ in path |
arbitrary file read/write |
| Command injection | CWE-78 | exec/shell_exec/system/proc_open, Process::run("... {$input}") |
code execution |
| XSS (auto-triggered) | CWE-79 | {!! $userInput !!}, Alpine x-html, raw JSON in <script> |
session/admin theft |
| Mass-assignment to privileged column | CWE-915 | $guarded = [] or fillable exposing role/is_admin + create($request->all()) |
privilege escalation |
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.
- 2d ago First seen · 114 lines · 58 tokens per session scan A 5ab39bf306eb
security-bounty-hunter is a skill published in the GitHub repository pekral/cursor-rules (6 stars, last pushed 6d ago), licensed MIT. It adds 58 tokens to every session and 1,561 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…