Skip to content
SkillModel-led19,946 tokens in use

bug-bounty

A full bug bounty pipeline in one skill: recon and scope, research, class-by-class testing, a seven-question validation gate and report hand-off, with routing to topic skills.

14,517 stars on the repository MIT Licenseelementalsouls/Claude-BugHunter · skills/bug-bounty
/plugin marketplace add elementalsouls/Claude-BugHunter /plugin install claude-bughunter@elementalsouls
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing bug-bounty costs

178tokens idle
19,946tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetectednetworkdetectedwrites filesdetectedgitdetectedcredentialsdetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size9/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Needs attention
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 209
  • Writes files−8

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 286
  • Reaches the network−10

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 297
  • Overrides the user's instructions−25

    tells the model to ignore its instructions or to hide what it does from the user

    SKILL.md, line 1100
  • Reads credentials−15

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 1266
  • Runs git commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 1539

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance84
  • Community68
  • Maturity28
  • Momentum40

bug-bounty is the master workflow skill of the Claude-BugHunter bundle. It guides a task from recon and program scope through research, vulnerability testing, validation and reporting, and routes to the topic skills for each bug class and report format.

Its rules tell the agent to read the full scope first, to ask whether the issue causes real harm to a real user and to drop theoretical findings. It also holds checklists for IDOR, SSRF, OAuth, file upload, race conditions, XSS, SQL injection, GraphQL, AI features, cache poisoning, request smuggling and CI/CD. It is intended for assets covered by a bug bounty program you have joined.

What You Get

  • Critical rules on scope, impact, time limits and automation
  • A cluster-hunting method that turns one bug into a chain, with known chains in a table
  • Checklists for the common web, API, mobile, AI and CI/CD bug classes
  • A seven-question gate, four pre-submission gates and a CVSS quick guide
  • Routing notes to the methodology, recon, triage and report-writing skills

Common Use Cases

  • Starting a bug bounty engagement and wanting a single skill that routes to the rest
  • Checking whether a finding clears the gate before spending time on a report
  • Looking up how to escalate a low-severity bug into a reportable chain

What Makes It Unique

It is the orchestrator of the bundle: it keeps the whole pipeline in one place and then hands off to specific skills by topic. It also carries operator notes on when to use the orchestrator, when to go straight to a class skill and why loading every hunting skill at once wastes context.

Under The Hood

The skill is one long SKILL.md of instructions with no bundled scripts. Following it, the agent runs shell commands for recon and testing such as subdomain discovery, URL collection, fuzzing and secret scanning, and it sends requests to the target hosts and to public sources. It writes output files and notes to the working folder, clones repositories with git, and its install notes fetch tools from the network. It also covers credentials: it shows patterns for finding leaked keys and tokens and tells the agent to prove what a found key can reach. One section on CI/CD workflows quotes prompt-injection phrases as examples of what to look for. Run it only against assets you are authorized to test.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers