Skip to content
SkillModel-led4,987 tokens in use

bugcrowd-reporting

Bugcrowd-specific reporting tactics: choose the VRT category, request a severity override, rebut out-of-scope clauses, cross-reference chained findings and order submissions.

14,523 stars on the repository MIT Licenseelementalsouls/Claude-BugHunter · skills/bugcrowd-reporting
/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 bugcrowd-reporting costs

171tokens idle
4,987tokens 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

Nothing detected: no shell, network, file writes, git or credentials in its files.

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
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size13/15
  • 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 →
Excellent

No findings.

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

bugcrowd-reporting is a skill for Claude that covers what is particular to Bugcrowd submissions. It explains how to search the Vulnerability Rating Taxonomy for the most specific accurate category, how to ask for a manual severity change when the default rating underrates impact, and why the severity request belongs in the first paragraph of the report body.

It also holds templates for answering out-of-scope clauses, advice on cross-referencing chained findings, guidance on QA versus production targets, researcher-side hygiene and an order for submitting several findings from one engagement. It complements the general report-writing skill in the same bundle.

What You Get

  • A search order for finding the right VRT category and a table of common finding-to-category mappings
  • A method for requesting a manual severity override with a short first paragraph
  • Rebuttal templates for common out-of-scope clauses
  • Advice on linking chained findings filed as separate reports
  • Researcher-side hygiene and a submission-order strategy for multi-finding engagements

Common Use Cases

  • Filing a Bugcrowd report whose default VRT priority looks too low
  • Answering a triager who cites an out-of-scope clause
  • Planning the order of several related submissions for one program

What Makes It Unique

It focuses on one platform’s mechanics, such as how the dropdown ties a default priority to each taxonomy node, and it insists on accuracy: pick the most specific true category, then argue severity in the open. Generic report templates for other platforms live in a separate skill.

Under The Hood

The skill is a single SKILL.md of guidance with no bundled scripts. It is a set of reporting tactics, report snippets and tables, so using it means the agent drafts text, and it may write the report to a file in the working folder. The text mentions test-account practices and account-state restoration after testing, and it quotes example report wording. It does not tell the agent to fetch pages or call services itself.

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