h-mmer
- 230 skills
- 0 followers
- 1.1k repo stars
- last month last updated
- ▌ Sast File Ranker 2 · h-mmerSource file attack surface ranker. Reads a repository, scores every source file 1-5 by exploitability. Outputs ranked JSON for per-file hunting. Use via /sast command.
- ▌ Sast Flow Tracer 2 · h-mmerTraces data flow from entry points to dangerous operations. Cross-file reasoning to determine which entries can reach which dangers, and what validation exists in between. MUST run on Opus for reasoning depth. Use via /sast command.
- ▌ Sast Entry Mapper 2 · h-mmerMaps entry points where untrusted data enters a source file. Lists every function that receives external input with data type, size constraints, and initial validation. Use via /sast command.
- ▌ Sast Gap Analyzer 2 · h-mmerAnalyzes validation gaps in data flows. Takes traced flows and identifies where checks are missing, insufficient, or bypassable. The 'interaction reasoning' step — finds bugs that exist in the gaps between individually correct-looking code. MUST run on Opus. Use via /sast command.
- ▌ Sast Danger Mapper 2 · h-mmerMaps dangerous operations in a source file: memory ops, type casts, arithmetic near trust boundaries, free/dealloc patterns. Pattern matching task — list what you see, don't speculate. Use via /sast command.
- ▌ Subdomain Takeover 2 · h-mmerSubdomain Takeover specialist (H1 #145). Use for finding dangling DNS records pointing to unclaimed cloud resources, expired services, or deprovisioned infrastructure.
- ▌
- ▌ Dast Devils Advocate 2 · h-mmerAdversarial validator for DAST findings. Attempts to DISPROVE each finding and DOWNGRADE severity. Catches inflated reports, unverified assumptions, and theoretical-only bugs. Dispatch after /validate PASS and before /report.
- ▌ Privilege Escalation 2 · h-mmerPrivilege Escalation specialist (H1 #26). Use for testing vertical and horizontal privilege escalation, role manipulation, admin endpoint access, and permission boundary violations.
- ▌ Sast Devils Advocate 2 · h-mmerAdversarial validator for SAST findings. Your ONLY job is to DISPROVE the candidate. Find every reason it's not exploitable. If you can't disprove it, it survives. Use via /sast command.
- ▌ Sast Exploit Builder 2 · h-mmerBuilds working exploits from confirmed SAST findings. Takes a confirmed crash, develops it into a full exploit. Tier 1 (DoS) → Tier 5 (code execution). Use via /sast command after PoC confirmation.
- ▌ Hunt LLM AI 3 · h-mmerHunting skill for LLM and Agentic AI vulnerabilities — direct + indirect prompt injection, ASCII smuggling data exfil, agentic tool-use abuse, system prompt leakage, vector DB cross-tenant, model server RCE, insecure output handling. Built from public bug bounty reports across HackerOne, Huntr, Project Zero, GitHub Security Advisories, plus 2024-2026 meta verified against NVD — Microsoft 365 Copilot ASCII Smuggling (Johann Rehberger Aug 2024 disclosure), CVE-2025-46059 LangChain GmailToolkit indirect prompt injection (CVSS 9.8), CVE-2025-68613 LangChain PythonREPLTool semantic RCE (CVSS 9.8), CVE-2024-46946 LangChain LLMSymbolicMathChain sympy.sympify, CVE-2025-27520 + CVE-2025-32375 + CVE-2024-2912 BentoML pickle, Ollama RCE family (CVE-2024-37032, CVE-2024-39722, CVE-2024-45436, CVE-2025-44779), CVE-2025-64496 Open WebUI Direct Connections SSE code injection (GHSA-cm35-v4vp-5xvx), CVE-2024-1483/1560/1594 MLflow path traversal. Covers OWASP LLM Top 10 v2025 (LLM01-LLM10) and OWASP Agentic AI Top 10 (AA-01 th
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ New 2 · h-mmer bundleCreate a new engagement workspace. Usage: /new <platform> <program> [--type web-app|api|mobile|smart-contract]
- ▌
- ▌ Hunt 2 · h-mmer bundleActive vulnerability hunting on a target. Loads scope, reads brain, detects tech stack, runs targeted tests with concrete payloads. Usage: /hunt target.com [--vuln-class idor|xss|ssrf|sqli|ssti|oauth|rce|race|graphql|upload|business-logic|llm-ai]
- ▌ Sync 2 · h-mmer bundleSync program scope, policy, and hacktivity from a bug bounty platform. Usage: /sync hackerone tesla or /sync bugcrowd uber
- ▌ Brain 2 · h-mmer bundleManage the engagement brain. Subcommands: 'init' to set up, 'brief <target>' for pre-flight, 'status' for overview, 'exhausted [target]' to see dead ends.
- ▌ Chain 2 · h-mmer bundleBuild deep exploit chains — dispatches chain-builder agent. Given bug A, recursively walks the chain graph. Usage: /chain (then describe bug A)
- ▌ Learn 2 · h-mmer bundleRecord a platform response and update learning. Usage: /learn <report_id> <status> [--bounty 500] [--vuln-type XSS]
- ▌ Report 2 · h-mmer bundleGenerate submission-ready reports for all confirmed findings. Runs dedup, PoC builder, quality check, and report writer. Usage: /report bounty or /report pentest
- ▌ Resume 2 · h-mmer bundleResume a previous hunt. Shows hunt history, untested endpoints, memory-informed suggestions. Usage: /resume target.com
- ▌ Status 2 · h-mmer bundleShow engagement dashboard with program info, scope, brain state, findings, agent activity, and cost estimate.
- ▌ Submit 2 · h-mmer bundleDraft and submit a vulnerability report to the bug bounty platform. Reads scope.yaml for platform/program, uses brain + findings for content. Always drafts first for review.
- ▌ Triage 2 · h-mmer bundleBatch-validate ALL findings through the 7-Question Gate. Kills weak findings in bulk. Usage: /triage
- ▌ Analyze 2 · h-mmer bundleAnalyze recon output with AI to suggest high-value targets and attack strategies. Usage: /analyze <target>
- ▌ Mindmap 2 · h-mmer bundleGenerate a text-based attack surface mindmap. Shows tech stack → vuln class → endpoint relationships. Usage: /mindmap <target>
- ▌ Monitor 2 · h-mmer bundleMonitor targets for changes. Usage: /monitor baseline (first run), /monitor check (detect changes), /monitor scope (check platform for scope updates)
- ▌ Dupcheck 2 · h-mmer bundleCheck if a vulnerability has already been reported. Searches platform hacktivity + local findings. Usage: /dupcheck <vuln_type> e.g. /dupcheck XSS in search endpoint
- ▌ Fullscan 2 · h-mmer bundleFull security assessment with brain coordination. Multi-phase, skips known-exhausted areas, builds on prior knowledge.
- ▌ Pipeline 2 · h-mmer bundlePrepare the battlefield — recon, scanning, and surface ranking. Stops before hunting. Run /hunt or /autopilot after. Usage: /pipeline or /pipeline <target>
- ▌ Remember 2 · h-mmer bundleLog a finding or pattern to persistent brain memory. Auto-fills from session context. Usage: /remember
- ▌ Validate 2 · h-mmer bundleValidate a finding through the 7-Question Gate + 4 gates. Kills weak findings FAST. Usage: /validate <finding description>
- ▌ Autopilot 2 · h-mmer bundleAutonomous hunt orchestrator. INSATIABLE in --autonomous mode: enforces an EXHAUSTION CONTRACT (26 canonical hunter classes, surface probe A-I, depth-engine ≥25 attempts/class, wall-clock floor 90 min/target, PRE-COMPLETION GATE before any summary). No early stops, no clarifying questions, no auxiliary-agent substitution. Usage: /autopilot target.com [--interactive|--autonomous] [--20m-off] [--resume]
- ▌ Correlate 2 · h-mmer bundleRun the finding correlation engine to discover attack chains from individual findings.
- ▌ Brain 3 · h-mmerCentral knowledge coordinator. Use BEFORE launching any other pentest agent to get context on what's already been tried. Also use AFTER any agent completes to record findings, exhausted vectors, and learned patterns. The brain prevents redundant work across sessions and agents.
- ▌ Monitor 3 · h-mmerContinuous monitoring agent for authorized bug bounty programs. Modes: 'baseline' captures initial state, 'check' detects changes, 'scope' re-syncs platform scope. Runs in background.
- ▌ Hunt LLM AI 2 · h-mmerHunting skill for LLM and Agentic AI vulnerabilities — direct + indirect prompt injection, ASCII smuggling data exfil, agentic tool-use abuse, system prompt leakage, vector DB cross-tenant, model server RCE, insecure output handling. Built from public bug bounty reports across HackerOne, Huntr, Project Zero, GitHub Security Advisories, plus 2024-2026 meta verified against NVD — Microsoft 365 Copilot ASCII Smuggling (Johann Rehberger Aug 2024 disclosure), CVE-2025-46059 LangChain GmailToolkit indirect prompt injection (CVSS 9.8), CVE-2025-68613 LangChain PythonREPLTool semantic RCE (CVSS 9.8), CVE-2024-46946 LangChain LLMSymbolicMathChain sympy.sympify, CVE-2025-27520 + CVE-2025-32375 + CVE-2024-2912 BentoML pickle, Ollama RCE family (CVE-2024-37032, CVE-2024-39722, CVE-2024-45436, CVE-2025-44779), CVE-2025-64496 Open WebUI Direct Connections SSE code injection (GHSA-cm35-v4vp-5xvx), CVE-2024-1483/1560/1594 MLflow path traversal. Covers OWASP LLM Top 10 v2025 (LLM01-LLM10) and OWASP Agentic AI Top 10 (AA-01 th
- ▌ Hunt Idor · h-mmerHunting skill for Insecure Direct Object Reference / Broken Object Level Authorization (BOLA — OWASP API1:2023). Built from 1,117 public IDOR bug bounty reports across HackerOne, Bugcrowd, Intigriti, GitHub Security Advisories, Huntr, plus 2024-2026 meta verified against NVD — Sam Curry's automotive chain (Kia/Hyundai/Ferrari), CVE-2026-30956 (OneUptime tenant header bypass CVSS 9.9), CVE-2025-64431 (Zitadel V2Beta Org API), CVE-2026-32131 (Zitadel Management API), CVE-2025-61876 (Inforcer tenant enumeration), CVE-2024-45719 (Apache Answer UUIDv1 token prediction), CVE-2024-50633 (Indico BOLA), plus the GraphQL field-level / nested-object pivot wave and agentic AI cross-tenant family (FastGPT, WeKnora, Paperclip). Use when hunting IDOR / BOLA / cross-tenant data access on web apps, APIs, GraphQL endpoints, multi-tenant SaaS, mobile apps, automotive/IoT platforms, and AI/ML inference servers.
- ▌ New · h-mmerCreate a new engagement workspace. Usage: /new <platform> <program> [--type web-app|api|mobile|smart-contract]
- ▌ Hunt LLM AI · h-mmerHunting skill for LLM and Agentic AI vulnerabilities — direct + indirect prompt injection, ASCII smuggling data exfil, agentic tool-use abuse, system prompt leakage, vector DB cross-tenant, model server RCE, insecure output handling. Built from public bug bounty reports across HackerOne, Huntr, Project Zero, GitHub Security Advisories, plus 2024-2026 meta verified against NVD — Microsoft 365 Copilot ASCII Smuggling (Johann Rehberger Aug 2024 disclosure), CVE-2025-46059 LangChain GmailToolkit indirect prompt injection (CVSS 9.8), CVE-2025-68613 LangChain PythonREPLTool semantic RCE (CVSS 9.8), CVE-2024-46946 LangChain LLMSymbolicMathChain sympy.sympify, CVE-2025-27520 + CVE-2025-32375 + CVE-2024-2912 BentoML pickle, Ollama RCE family (CVE-2024-37032, CVE-2024-39722, CVE-2024-45436, CVE-2025-44779), CVE-2025-64496 Open WebUI Direct Connections SSE code injection (GHSA-cm35-v4vp-5xvx), CVE-2024-1483/1560/1594 MLflow path traversal. Covers OWASP LLM Top 10 v2025 (LLM01-LLM10) and OWASP Agentic AI Top 10 (AA-01 th
- ▌
- ▌ Hunt · h-mmerActive vulnerability hunting on a target. Loads scope, reads brain, detects tech stack, runs targeted tests with concrete payloads. Usage: /hunt target.com [--vuln-class idor|xss|ssrf|sqli|ssti|oauth|rce|race|graphql|upload|business-logic|llm-ai]
- ▌ Sync · h-mmerSync program scope, policy, and hacktivity from a bug bounty platform. Usage: /sync hackerone tesla or /sync bugcrowd uber
- ▌
- ▌ Brain · h-mmerManage the engagement brain. Subcommands: 'init' to set up, 'brief <target>' for pre-flight, 'status' for overview, 'exhausted [target]' to see dead ends.
- ▌ Chain · h-mmerBuild deep exploit chains — dispatches chain-builder agent. Given bug A, recursively walks the chain graph. Usage: /chain (then describe bug A)
- ▌ Learn · h-mmerRecord a platform response and update learning. Usage: /learn <report_id> <status> [--bounty 500] [--vuln-type XSS]
- ▌ Report · h-mmerGenerate submission-ready reports for all confirmed findings. Runs dedup, PoC builder, quality check, and report writer. Usage: /report bounty or /report pentest
- ▌ Resume · h-mmerResume a previous hunt. Shows hunt history, untested endpoints, memory-informed suggestions. Usage: /resume target.com
- ▌ Status · h-mmerShow engagement dashboard with program info, scope, brain state, findings, agent activity, and cost estimate.
- ▌ Submit · h-mmerDraft and submit a vulnerability report to the bug bounty platform. Reads scope.yaml for platform/program, uses brain + findings for content. Always drafts first for review.
- ▌ Triage · h-mmerBatch-validate ALL findings through the 7-Question Gate. Kills weak findings in bulk. Usage: /triage
- ▌
- ▌ Analyze · h-mmerAnalyze recon output with AI to suggest high-value targets and attack strategies. Usage: /analyze <target>
- ▌ Mindmap · h-mmerGenerate a text-based attack surface mindmap. Shows tech stack → vuln class → endpoint relationships. Usage: /mindmap <target>
- ▌ Monitor · h-mmerMonitor targets for changes. Usage: /monitor baseline (first run), /monitor check (detect changes), /monitor scope (check platform for scope updates)
- ▌ Quality · h-mmerScore a report draft before submission. Usage: /quality <draft-path-or-finding-description>
- ▌ Surface · h-mmerShow ranked attack surface for a target. Invokes recon-ranker agent. Usage: /surface target.com
- ▌ Dupcheck · h-mmerCheck if a vulnerability has already been reported. Searches platform hacktivity + local findings. Usage: /dupcheck <vuln_type> e.g. /dupcheck XSS in search endpoint
- ▌ Fullscan · h-mmerFull security assessment with brain coordination. Multi-phase, skips known-exhausted areas, builds on prior knowledge.
- ▌ Pipeline · h-mmerPrepare the battlefield — recon, scanning, and surface ranking. Stops before hunting. Run /hunt or /autopilot after. Usage: /pipeline or /pipeline <target>
- ▌ Remember · h-mmerLog a finding or pattern to persistent brain memory. Auto-fills from session context. Usage: /remember
- ▌ Validate · h-mmerValidate a finding through the 7-Question Gate + 4 gates. Kills weak findings FAST. Usage: /validate <finding description>
- ▌
- ▌ Autopilot · h-mmerAutonomous hunt orchestrator. INSATIABLE in --autonomous mode: enforces an EXHAUSTION CONTRACT (26 canonical hunter classes, surface probe A-I, depth-engine ≥25 attempts/class, wall-clock floor 90 min/target, PRE-COMPLETION GATE before any summary). No early stops, no clarifying questions, no auxiliary-agent substitution. Usage: /autopilot target.com [--interactive|--autonomous] [--20m-off] [--resume]
- ▌ Correlate · h-mmerRun the finding correlation engine to discover attack chains from individual findings.
- ▌
- ▌
- ▌ Hunt Business Logic · h-mmer bundleHunting skill for business-logic vulnerabilities (CWE-840 Business Logic Errors, CWE-841 Improper Enforcement of Behavioral Workflow, CWE-639 Authorization Bypass via User-Controlled Key in business contexts, CWE-362 race conditions on financial flows). Built from 44 corpus reports plus 8.8K shared-platform reports across HackerOne, Bugcrowd, Huntr, GitHub Security Advisories, plus 2024-2026 meta verified against NVD — Lilishop coupon overpurchasing (CVE-2024-50654 CVSS 7.5), WWBN AVideo wallet double-spend TOCTOU (CVE-2026-34368, GHSA-h54m-c522-h6qr), Keycloak 2FA bypass (CVE-2025-3910, GHSA-5jfq-x6xp-7rw2), AlegroCart 1.2.9 negative-quantity price manipulation (Andrey Stoykov SecLists Apr 2025), Bagisto cart price manipulation (Rudransh Singh Rajpurohit Sep 2025), Doppler free-trial reset (Aditya Sunny Dec 2024), Stripe hasEverTrialed bypass (better-auth
- ▌
- ▌
- ▌ Sast · h-mmer bundleSource code vulnerability hunting (SAST). Decomposes analysis into specialized passes: map entry points, map dangerous ops, trace flows, find gaps, adversarial validation, exploit. Usage: /sast <repo_path> [--lang c|cpp|rust|java|python|go|php] [--min-score 4] [--max-files 30] [--skip-static] [--best-of N]
- ▌ Quickscan · h-mmer bundleRun a quick security scan on a target. Consults the Brain first, validates scope, runs passive recon + vuln scan in parallel.
- ▌ Recon · h-mmerReconnaissance agent for target enumeration. Use for subdomain discovery, port scanning, service fingerprinting, tech stack identification, and OSINT gathering. Specify scope and depth: 'passive' for DNS/cert/OSINT only, 'active' for port scans and probing, 'deep' for comprehensive enumeration.
- ▌ Validator · h-mmerFinding validator. Runs 7-Question Gate + 4-gate checklist. Kills weak/theoretical findings FAST before any report writing. Output: PASS, KILL, DOWNGRADE, or CHAIN REQUIRED.
- ▌ Correlator · h-mmerFinding correlation engine. Use AFTER multiple agents have reported findings to discover attack chains. Combines individual findings into higher-impact chains (e.g., open redirect + CORS + SSRF = token theft). Run periodically or before final reporting.
- ▌ Rce Hunter · h-mmerRemote Code Execution specialist (H1 #70). Use for testing command injection, template injection (SSTI), deserialization, expression language injection, and any vector that achieves server-side code execution.
- ▌ Xss Hunter · h-mmerXSS specialist covering reflected (H1 #60), stored (H1 #61), and DOM (H1 #62). Dispatcher passes subtype — 'reflected', 'stored', or 'dom' — in the task; falls back to inference from target. Use for parameter reflection, persisted inputs (comments/profiles/uploads/filenames), or client-side source→sink analysis.
- ▌ Xxe Hunter · h-mmerXXE specialist (H1 #63). Use for testing XML parsing endpoints, file upload processors, SOAP services, SVG handlers, and any feature accepting XML input.
- ▌ Auth Tester · h-mmerAuthentication and session management testing agent. Use for login bypass, session fixation, password reset flow abuse, MFA bypass, OAuth flaws, and privilege escalation testing. Provide the application URL and any credentials for testing.
- ▌ Cloud Recon · h-mmerCloud misconfiguration scanner. Use for S3 bucket enumeration, Azure blob discovery, GCP storage checks, exposed cloud services, and cloud metadata analysis. Provide target domain or known cloud identifiers.
- ▌ Cors Hunter · h-mmerCORS Misconfiguration specialist (H1 #58). Use for testing cross-origin resource sharing policies, origin reflection, null origin bypass, and credential-bearing cross-origin requests.
- ▌ Csrf Hunter · h-mmerCSRF specialist (H1 #57). Use for testing state-changing actions without proper token validation, SameSite cookie bypass, and CSRF in JSON/API endpoints.
- ▌ File Upload · h-mmerFile Upload vulnerability specialist (H1 #39). Use for testing upload restrictions, content-type bypass, extension filtering, path traversal in filenames, and web shell upload scenarios.
- ▌ Idor Hunter · h-mmerIDOR / BOLA specialist (H1 #55, OWASP API1:2023). Use for testing insecure direct object references and broken object level authorization across web apps, APIs, GraphQL endpoints, multi-tenant SaaS, mobile, automotive/IoT, and AI inference servers.
- ▌ JS Analyzer · h-mmerJavaScript static analysis agent for client-side security review. Use for analyzing JS bundles, finding hardcoded secrets, tracing DOM XSS source-sink flows, identifying postMessage handlers, extracting API endpoints, and reviewing client-side access controls. Provide URLs or local JS file paths.
- ▌ Poc Builder · h-mmerBug bounty PoC and report builder. Use after confirming a vulnerability to create minimal reproduction steps, self-contained HTML demonstration pages, curl-based reproduction scripts, and platform-ready report drafts for HackerOne/Bugcrowd/Intigriti.
- ▌ Sast Hunter · h-mmerFocused PoC builder for SAST candidates. Receives a SPECIFIC candidate vulnerability that survived adversarial validation. Writes a PoC, compiles, runs with ASan, confirms or rejects. Use via /sast command.
- ▌ Scope Check · h-mmerTarget scope validation agent. Use BEFORE any active testing to verify targets are in scope. Provide the target and the program name or scope file. Checks against .scope.txt, scope.yaml, and fetches live program scope from HackerOne/Bugcrowd/Intigriti APIs if configured.
- ▌ Sqli Hunter · h-mmerSQL Injection specialist (H1 #67). Use for error-based, blind boolean, blind time-based, UNION-based, and out-of-band SQLi testing. Provide target endpoints with injectable parameters.
- ▌ Ssrf Hunter · h-mmerSSRF vulnerability hunting specialist. Use for testing URL-accepting parameters, webhook endpoints, file import features, and any server-side request functionality. Provide target endpoints with URL parameters.
- ▌ Ssti Hunter · h-mmerServer-Side Template Injection specialist. Covers Jinja2 (H1 #74), Twig, Velocity, FreeMarker, ERB, Handlebars, Thymeleaf. Use for any rule-engine, comment/message rendering, PR automation, admin template, or user-customizable template surface. Systematic blocklist mapper + CVE bypass runner + runtime-vs-parse distinguisher.
- ▌ OAUTH Hunter · h-mmerOAuth 2.0 / 2.1, OpenID Connect (OIDC), SAML SSO, and JWT specialist. Dispatcher passes subtype — 'oauth', 'oidc', 'saml', or 'jwt' — in the task; falls back to inference. Use for redirect_uri / returnTo flaws, state/nonce/PKCE bypass, alg confusion (none/HS-with-RS-key/kid/jku), SAML XSW + comment injection + assertion replay, OIDC ID token validation gaps, code/token leak channels, cross-tenant impersonation, PKCE downgrade, and any flow involving a code, access_token, id_token, assertion, client_id, client_secret, code_verifier, code_challenge, kid, or jku parameter.
- ▌ Recon Ranker · h-mmerAttack surface ranker. Takes recon output + brain data, produces P1/P2/Kill prioritized attack plan with concrete curl commands for each P1 target. Use after recon to decide what to test first.