secrets-hunt

A credential scanner for finding leaked API keys, tokens, and other secrets in files, Git history, JavaScript bundles, or a GitHub organization. It uses whichever supported scanner is installed and can fall back to regular-expression matching.

In plain words
What is it for?
Checking project directories, Git repositories, reconnaissance JavaScript bundles, or GitHub organizations for leaked credentials, with live-key verification when the selected scanner supports it.
Why use it?
It helps locate exposed credentials across both current files and past code, including secrets accidentally shipped in browser JavaScript.

Command

Install

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.

agentmods
npx agentmods add commands/awarexone/agentic-bug-hunter/secrets-hunt
Clone the repo
git clone --depth 1 https://github.com/Awarexone/Agentic-Bug-Hunter
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 566 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00566
Opus 5 $0.00000 $0.00283
Sonnet 5 $0.00000 $0.00113
Haiku 4.5 $0.00000 $0.00057

Measured 3d ago against content hash 5f988d23bc7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

secrets-hunt scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `streaak/keyhacks` shows the canonical curl-one-liner per provider.
commands/secrets-hunt.md · 54 lines

What it actually says

/secrets-hunt

Find leaked API keys, tokens, and credentials — verified when possible.

Usage

/secrets-hunt --filesystem /path/to/project
/secrets-hunt --git https://github.com/target/repo
/secrets-hunt --js-bundle recon/target.com
/secrets-hunt --github-org acme-corp           # needs GITHUB_TOKEN env

Scanners (best installed wins; the script runs whichever it finds)

Scanner Strength
trufflehog Verifies live keys against the issuer API (AWS/Slack/Stripe/GH/...)
noseyparker Fast on massive git histories with low false-positive rate
gitleaks Opinionated rule pack — solid default for repos

If none are installed the script still runs a regex fallback over the target so something useful comes out — but you should install at least trufflehog (brew install trufflehog) for the verified-only output.

Why this is high-impact

  • Leaked AWS / GCP / Slack / Twilio / OpenAI tokens are typically rated High to Critical ($1k–$10k+) on H1.
  • Verified-only mode kills the noisy false positives that get reports closed.
  • JS-bundle mode is the easiest win — companies regularly ship tokens in bundled frontend JavaScript.

Verifying the find

When a hit comes back, verify the key works the right way before submitting:

  • streaak/keyhacks shows the canonical curl-one-liner per provider.
  • Submit only verified, in-scope keys.
  • Don't pivot off the key (no further actions on the cloud account beyond proving it works) — most programs treat that as out-of-scope.

Output

findings/secrets/<timestamp>/ containing:

  • trufflehog.jsonl — verified hits (high-confidence)
  • noseyparker.jsonl — match groups across the history
  • gitleaks.json — opinionated default-rule hits
  • regex_hits.txt — regex fallback (manual triage required)
Changes

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.

  1. 3d ago First seen · 54 lines · 0 tokens per session scan A 5f988d23bc7f

Subscribe to this mod's changes

secrets-hunt is a command published in the GitHub repository Awarexone/Agentic-Bug-Hunter (4,651 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 566 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other commands, from other repositories

recon

Run full recon pipeline on a target — subdomain enum (Chaos API + subfinder), live host discovery (dnsx + httpx), URL crawl (katana + waybackurls + gau), gf pattern classification, nuclei scan. Outputs to recon/ / directory. Usage: /recon target.com.

elementalsouls/Claude-BugHunter · 65 tokens

hunt

Active vulnerability hunting. Two-track dispatcher — asks Red Team vs WAPT, hands off to hunt-dispatch skill and sibling commands. Usage: /hunt target.com | /hunt .target.com | /hunt targets.txt [--vuln-class X] [--source-code P] [--chrome].

elementalsouls/Claude-BugHunter · 63 tokens

token-scan

Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP lock bypass, authority retention, bonding curve exploits, fake renounce, sandwich amplification). Manual 8-class grep audit (with an optional automated scanner if present). Usage: /token-scan [--chain solana].

elementalsouls/Claude-BugHunter · 79 tokens

autopilot

Run autonomous hunt loop on a target — scope check → recon → rank surface → hunt → validate → report with configurable checkpoints. Usage: /autopilot target.com [--paranoid|--normal|--yolo].

elementalsouls/Claude-BugHunter · 49 tokens

triage

Quick 7-Question Gate triage on a finding before writing a report. Kills N/A submissions before they happen. Faster than /validate — for quick go/no-go decisions. Usage: /triage.

elementalsouls/Claude-BugHunter · 45 tokens

validate

Validate a finding — runs 7-Question Gate + 4-gate checklist. Kills weak findings before report writing. Prevents N/A submissions that hurt validity ratio. Usage: /validate.

elementalsouls/Claude-BugHunter · 41 tokens