Skip to content
Conduit

skill

bug-bounty-triage

Agent skill for rigorous bug bounty report triage, validation, severity escalation, and submission-ready reporting.

Sequester-AG/bug-bounty-triagecommunitylistedunreviewed
Use skill

Set up

Skills are installed by placing their folder where your agent loads skills.

Download ZIP from GitHub Open the repository

The download comes from github.com/Sequester-AG/bug-bounty-triage itself, not from our server, so what you get is exactly what its author published.

Install instructions come from the README

Skills do not use an MCP config. Follow the steps in the README below.

README

synced Oct 15, 2026

bug-bounty-triage

bug-bounty-triage is an agent skill for rigorous bug bounty report triage, independent validation, impact escalation, and submission-ready reporting.

It is designed to help an agent:

  • reproduce findings end to end when testing is authorized;
  • separate observed evidence from inference;
  • reject weak or non-actionable reports before submission;
  • pursue the highest defensible impact without overstating severity; and
  • produce concise, evidence-heavy Markdown reports for bug bounty platforms.

Responsible use

Use this skill only on systems you own or are explicitly authorized to test. Invoking the skill does not grant permission to test a target, exceed a program's scope, access unrelated data, or perform destructive actions.

The skill may preserve sensitive evidence in generated reports when the user supplies it. Review generated files before sharing or committing them, and follow the applicable bug bounty program's rules.

Installation

Skills CLI

npx skills add Sequester-AG/bug-bounty-triage --skill bug-bounty-triage

Codex

git clone https://github.com/Sequester-AG/bug-bounty-triage.git ~/.codex/skills/bug-bounty-triage

Agent skills directory

git clone https://github.com/Sequester-AG/bug-bounty-triage.git ~/.agents/skills/bug-bounty-triage

Supporting skills and CLIs

The full live-validation workflow uses agent-browser for browser automation and agent-email-cli for disposable test inboxes.

Install both agent skills:

npx skills add https://github.com/vercel-labs/agent-browser --skill agent-browser
npx skills add https://github.com/zaddy6/agent-email-skill --skill agent-email-cli

The skills provide agent instructions. Install their corresponding command-line tools for live execution:

npm install -g agent-browser
agent-browser install
npm install -g @zaddy6/agentemail

Usage

Invoke the skill with a report, vulnerability description, or target and finding:

Use $bug-bounty-triage to validate this report and determine whether it is ready to submit: <report>

For live validation, provide the relevant authorization and scope. The complete workflow can use browser automation, direct HTTP requests, and disposable email accounts when those capabilities are available in the host environment. If live testing is unavailable, the skill should state what remains unverified.

Output

For a supported, submission-ready finding, the skill writes a Markdown report named from the target and vulnerability class, such as:

example-com-idor.md

Internal triage commentary stays outside the submission file.

Repository contents

  • SKILL.md — skill metadata, workflow, validation gates, escalation guidance, and report format
  • LICENSE — MIT License

License

MIT

↑↓ navigate openesc close