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 ShulkwiSEC/bb-huge --skill analyze-cvegit clone --depth 1 https://github.com/ShulkwiSEC/bb-hugeWrote 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/shulkwisec/bb-huge/analyze-cve)<a href="https://agentmods.dev/skills/shulkwisec/bb-huge/analyze-cve"><img src="https://agentmods.dev/badge/skills/shulkwisec/bb-huge/analyze-cve.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 | $0.00000 | $0.03999 |
| Opus 5 | $0.00000 | $0.01999 |
| Sonnet 5 | $0.00000 | $0.00800 |
| Haiku 4.5 | $0.00000 | $0.00400 |
Grade A, and why
analyze-cve 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 8d 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 — 430 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CVE Vulnerability Analysis Workflow
Purpose
This workflow provides a structured methodology for analyzing whether a CVE affecting a project dependency poses a real security risk. It:
- Traces vulnerable code paths in your application
- Analyzes dataflow from user input to vulnerable functions
- Creates proof-of-concept HTTP requests for Burp Suite validation
Language/Framework Agnostic: Works with Python, Node.js, Java, Go, Ruby, PHP, and more.
Important Assumptions
Trust User-Provided Information
- The user has already verified the CVE and version through SCA tools (Snyk, Dependabot, GitHub Security, etc.)
- Trust the dependency name, version, and CVE information provided - do not require verification
- Do not fail if dependency files are missing or incomplete - focus on code analysis
- Do not stop if packages aren't installed locally - many projects use private artifactories or complex build processes
- Your job is to analyze CODE USAGE, not verify dependency versions
What This Means
- If the user says "analyze CVE-X in package Y version Z", proceed with the analysis
- Look for usage of the vulnerable code in the application
- If you can't find dependency files, document this but continue the analysis
- If the package isn't locally installed, work with the CVE description to understand what to look for
CHAIN COMMITMENTS — DECLARE BEFORE STARTING
Read this before executing any workflow phase. Commit to MANDATORY chains before your first tool call.
| Trigger | Chain | Mandatory? | Claude Code | opencode |
|---|---|---|---|---|
After session(action="complete") (confirmed exploitable finding) |
/gh-export |
OPTIONAL — user request only | Skill(skill="gh-export") |
cat ~/.config/opencode/commands/gh-export.md |
| Exploitable CVE confirmed + live target available | /web-exploit |
OPTIONAL | Skill(skill="web-exploit") |
cat ~/.config/opencode/commands/web-exploit.md |
| Exploitable CVE confirmed + Metasploit module available | /metasploit |
OPTIONAL | Skill(skill="metasploit") |
cat ~/.config/opencode/commands/metasploit.md |
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.
- 8d ago First seen · 430 lines · 0 tokens per session scan A d745526fe1cb
analyze-cve is a skill published in the GitHub repository ShulkwiSEC/bb-huge (22 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,999 tokens. 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
bugcrowd-reporting
Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity override when VRT defaults underrate impact, severity-request paragraph as first body section, OOS-clause rebuttal templates (rate limiting on auth-flow endpoints…
skill-context-detection
Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type.
skill-copilot-provider
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode.
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
skill-security-framing
URL validation and content sanitization for untrusted sources — use when handling external input safely.
race
Race condition / TOCTOU playbook — limit overrun (one-time codes used twice, gift cards spent twice), single-packet attack (last-byte sync) to force parallel processing, and state-confusion races (file upload + read, order before payment). Use when timing-sensitive logic could be abused — one-time codes, coupons/gift…