A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise identity + infrastructure attack matrices.
Python ai-securityanthropicapplication-securitybug-bountybugbountybugcrowdclaudeclaude-codeclaude-skillsethical-hackinghackeroneoffensive-securitypentestingred-teamsecurity-toolsweb-security
fix: add missing name: field to all 14 command frontmatter blocks
xiaolaia5aa78e2c983
diff --git a/commands/autopilot.md b/commands/autopilot.mdindex a011162..7f86e75 100644--- a/commands/autopilot.md+++ b/commands/autopilot.md@@ -1,4 +1,5 @@---+name: autopilotdescription: 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]---diff --git a/commands/chain.md b/commands/chain.mdindex 79a9182..91748dc 100644--- a/commands/chain.md+++ b/commands/chain.md@@ -1,4 +1,5 @@---+name: chaindescription: Build an exploit chain — given bug A, finds B and C to combine for higher severity and payout. Knows common chain patterns: IDOR→ATO, SSRF→cloud metadata, XSS→ATO, open redirect→OAuth theft, S3→bundle→secret→OAuth. Usage: /chain---diff --git a/commands/hunt.md b/commands/hunt.mdindex 6d907b5..6f633cb 100644--- a/commands/hunt.md+++ b/commands/hunt.md@@ -1,4 +1,5 @@---+name: huntdescription: 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]---diff --git a/commands/intel.md b/commands/intel.mdindex 4665dc5..fc32674 100644--- a/commands/intel.md+++ b/commands/intel.md@@ -1,4 +1,5 @@---+name: inteldescription: On-demand intelligence fetch for a target — CVEs, disclosed reports, new features. Wraps learn.py + hunt memory context. Usage: /intel target.com---diff --git a/commands/memory-gc.md b/commands/memory-gc.mdindex 0bb2235..14492b5 100644--- a/commands/memory-gc.md+++ b/commands/memory-gc.md@@ -1,4 +1,5 @@---+name: memory-gcdescription: Inspect or rotate hunt-memory JSONL files (audit.jsonl, patterns.jsonl, journal.jsonl). Caps file size and keeps N rotated backups so memory does not grow unbounded.---diff --git a/commands/pickup.md b/commands/pickup.mdindex cba6d4f..93c750d 100644--- a/commands/pickup.md+++ b/commands/pickup.md@@ -1,4 +1,5 @@---+name: pickupdescription: Pick up a previous hunt on a target — shows hunt history, untested endpoints, and memory-informed suggestions. Usage: /pickup target.com---diff --git a/commands/recon.md b/commands/recon.mdindex 9ad9274..256eb4b 100644--- a/commands/recon.md+++ b/commands/recon.md@@ -1,4 +1,5 @@---+name: recondescription: 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/<target>/ directory. Usage: /recon target.com---diff --git a/commands/remember.md b/commands/remember.mdindex 4ffbb26..bff5550 100644--- a/commands/remember.md+++ b/commands/remember.md@@ -1,4 +1,5 @@---+name: rememberdescription: Log current finding or successful pattern to hunt memory. Auto-fills from /validate output if available. Usage: /remember---diff --git a/commands/report.md b/commands/report.mdindex 1ad5c06..550bb93 100644--- a/commands/report.md+++ b/commands/report.md@@ -1,4 +1,5 @@---+name: reportdescription: Write a submission-ready bug bounty report. Generates H1/Bugcrowd/Intigriti/Immunefi format with CVSS 3.1 score, proof of concept, impact statement, and remediation. Run /validate first. Usage: /report---diff --git a/commands/surface.md b/commands/surface.mdindex 5003135..edcc6a2 100644--- a/commands/surface.md+++ b/commands/surface.md@@ -1,4 +1,5 @@---+name: surfacedescription: Show ranked attack surface for a target based on recon output + hunt memory. Invokes recon-ranker agent. Usage: /surface target.com---diff --git a/commands/token-scan.md b/commands/token-scan.mdindex 28c2bdb..aaadb04 100644--- a/commands/token-scan.md+++ b/commands/token-scan.md@@ -1,4 +1,5 @@---+name: token-scandescription: 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). Runs automated token_scanner.py + manual 8-class audit. Usage: /token-scan <contract_path_or_dir> [--chain solana]---diff --git a/commands/triage.md b/commands/triage.mdindex 1c7fa0d..845a03c 100644--- a/commands/triage.md+++ b/commands/triage.md@@ -1,4 +1,5 @@---+name: triagedescription: 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---diff --git a/commands/validate.md b/commands/validate.mdindex a5f21ec..e01419c 100644--- a/commands/validate.md+++ b/commands/validate.md@@ -1,4 +1,5 @@---+name: validatedescription: 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---diff --git a/commands/web3-audit.md b/commands/web3-audit.mdindex c012d78..a9e4be1 100644--- a/commands/web3-audit.md+++ b/commands/web3-audit.md@@ -1,4 +1,5 @@---+name: web3-auditdescription: Smart contract security audit — runs through 10 bug class checklist (accounting desync, access control, incomplete path, off-by-one, oracle errors, ERC4626, reentrancy, flash loan, signature replay, proxy/upgrade). Applies pre-dive kill signals first. Generates Foundry PoC template for confirmed findings. Usage: /web3-audit <contract.sol>---