leak-triage-and-validation — Claude Code skill: install
The leak-triage-and-validation Claude Code skill sorts leaked tokens, keys, and repositories. It checks credentials and their value, then prepares findings for responsible disclosure.
LicenseRef-Proprietary ★ 326 updated 2026-11-01
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill leak-triage-and-validation -a claude-codeWhat leak-triage-and-validation does
The skill filters a noisy leak into findings that pass validation and merit a report. It classifies candidate secrets, removes duplicates, checks account identity and permissions with read-only requests, then scores findings by value and ROI.
Raw artifacts stay in an isolated vault on the VPS. The model sees only metadata from triage.json, never the secret values. Candidate extraction can use gitleaks, TruffleHog, or regular expressions with entropy checks.
The skill profiles the owner and hands the finding and profile to disclosure-communication or an equivalent skill. It drafts a redacted report and outreach message; a person must approve anything sent. Contacts and follow-up outcomes go into a tracker. Credentials must not be used to access accounts, and checks must not write data.
What it helps with
- deduplicate credentials found in a leak
- check whether a key is live and what permissions it has
- rank findings by value and ROI
- draft a redacted disclosure report for human approval
- track contacts and disclosure outcomes
Example prompts for the agent
- Sort this leak, check credentials with read-only requests, and rank findings by ROI.
- Review metadata for this private repository and decide what belongs in a report.
- Profile the owner and prepare the finding for
disclosure-communication; do not send a message.
How to install leak-triage-and-validation
1Skills CLI (Vercel)
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill leak-triage-and-validation -a claude-code2Manually: put the files in place
~/.claude/skills/leak-triage-and-validation/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/leak-triage-and-validation/
1Skills CLI (Vercel)
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill leak-triage-and-validation -a codex2Manually: put the files in place
.agents/skills/leak-triage-and-validation/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill leak-triage-and-validation -a cursor2Manually: put the files in place
.cursor/skills/leak-triage-and-validation/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install mrhlaingbwardev/agentic-hacking-skills skills/leak-triage-and-validation2Manually: put the files in place
.github/skills/leak-triage-and-validation/SKILL.md1Skills CLI (Vercel)
npx skills add mrhlaingbwardev/agentic-hacking-skills --skill leak-triage-and-validation -a gemini-cli2Platform CLI
gemini skills install https://github.com/mrhlaingbwardev/agentic-hacking-skills --path skills/leak-triage-and-validationManually: put the files in place
.devin/skills/leak-triage-and-validation/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about leak-triage-and-validation
How do I install leak-triage-and-validation in Claude Code?
Run npx skills add mrhlaingbwardev/agentic-hacking-skills --skill leak-triage-and-validation -a claude-code. The skill file is at ~/.claude/skills/leak-triage-and-validation/SKILL.md.
What does leak-triage-and-validation do?
It filters leaked credentials, checks identity and permissions through read-only requests, and scores findings by value and ROI. It prepares disclosure materials, which require human approval before sending.
How does the skill handle secret values?
Raw artifacts stay in an isolated VPS vault, while the model receives metadata and hash references. The skill does not use credentials to access accounts or read their contents.