skills

Deep web exploitation beyond initial scanning. Covers SQLi (blind, OOB, second-order), NoSQL injection, GraphQL injection (introspection, batching, mutation abuse), XSS (reflected/stored/DOM with source-sink analysis), SSTI (Jinja2/Twig/Freemarker/ERB RCE), SSRF chains, file upload bypass (polyglots), XXE (blind, DOCX/SVG, Content-Type switching), deserialization (Java/PHP/Python/.NET), command injection, path traversal / LFI wrapper bypasses, race conditions, CSRF, JWT attacks (none/key confusion/kid injection), HTTP request smuggling (CL.TE/TE.CL/H2), CRLF injection, open redirect chains, CORS exploitation, web cache deception/poisoning, OAuth misconfiguration, prototype pollution, session management, and business logic flaws. Uses sqlmap, commix, xsser, wapiti, davtest, and manual http payloads - every technique includes real payloads and code. Chains from /pentester or /api-security, into /post-exploit on RCE, and into /ai-redteam when an LLM/AI endpoint is found.

Reverse shell generation and listener management. Generates platform-specific reverse shell payloads (bash, python, php, powershell, java, ruby, perl, netcat, socat, msfvenom) and sets up listeners in the Kali container. Supports one-liner generation, encoded payloads for WAF/filter bypass, listener setup with session capture, and shell stabilization. Chains from /pentester, /metasploit, or /post-exploit when command execution is confirmed.

White-box source code security review structured around OWASP ASVS 5.0 (427 verification requirements across 16 chapters). Reads and understands application source code to build a security-aware knowledge base that enriches all downstream skills. Covers: tech stack identification, route/endpoint mapping, authentication and authorization architecture, dangerous function patterns, source-to-sink data flow tracing, IaC review, dependency analysis, ASVS compliance mapping, and LLM integration security (prompt injection, tool abuse, output handling, RAG poisoning, MCP server patterns). When LLM/AI framework usage is detected, automatically reviews OWASP LLM Top 10 patterns from source code and chains into /ai-redteam with white-box context for live endpoint testing. Chains into /pentester, /threat-modeling, /web-exploit, /api-security, /cloud-security, /analyze-cve, /credential-audit, and /ai-redteam — providing white-box context that transforms black-box testing into targeted, informed assessment.

Formats all confirmed pentest findings from findings.json into copy-pasteable GitHub issue markdown blocks, following the AppSec reporting guide template.

Post-exploitation workflow. Covers privilege escalation (Linux SUID/sudo/kernel, Windows UAC/service/token), persistence assessment, local enumeration, credential harvesting, and pivot preparation. Structured workflows for Linux and Windows targets using impacket, netexec, john, linpeas/winpeas, and standard Kali tools. Includes kernel exploit reference tables, GTFOBins exploitation chains, Potato attack selection, Docker/container escapes, DLL hijacking, SSH key harvesting, credential recovery from memory, and Windows token manipulation. Chains from /pentester or /credential-audit when access is obtained.

Software supply-chain and CI/CD security assessment. Covers dependency confusion (internal/private package names that resolve on public registries — extracted from package.json, requirements.txt, pom.xml, go.mod, Gemfile, .csproj), typosquatting and namespace hijacking, lockfile integrity and resolved-URL tampering, malicious install hooks (npm postinstall, pip setup.py, gem extensions), and unmaintained/abandoned-package takeover risk. Plus CI/CD pipeline review: GitHub Actions / GitLab CI / CircleCI misconfigurations — pull_request_target abuse, unpinned action SHAs, secrets leaked in logs, over-broad OIDC trust, and poisoned pipeline execution (PPE, direct and indirect). Assesses SLSA provenance gaps. White-box first: reads manifests, lockfiles, and workflow YAML from a local codebase. Uses semgrep, trufflehog, and registry probes. Chains from /codebase or /pentester; into /analyze-cve for confirmed vulnerable versions and /cloud-security when a pipeline holds cloud OIDC trust.

Cloud-native identity federation attacks across AWS, Azure, and GCP. Covers OIDC CI/CD trust abuse (IAM role trust policies that trust token.actions.githubusercontent.com, GitLab, CircleCI, or Terraform Cloud with over-broad sub/aud conditions), workload-identity abuse (EKS IRSA, GKE Workload Identity, AKS pod-managed-identity — Kubernetes ServiceAccount token to AssumeRoleWithWebIdentity to cloud credentials), and the full SSRF to IMDSv2 to role to credential chain walked end to end. Also covers ECS/Fargate task-role metadata (169.254.170.2), Azure IMDS managed-identity token theft, GCP metadata service-account tokens, and cloud-credential pivoting from a shell (~/.aws/credentials, gcloud creds, kubeconfig, CI env, projected SA tokens). Taught as attack PATTERNS to reason from. Uses aws/az/gcloud CLIs, kubectl, curl, jwt_tool, and http probing. Chains from /pentester, /cloud-security, or /web-exploit (on a confirmed SSRF); into /post-exploit and /cloud-security once credentials are obtained.

SAML, enterprise SSO, SCIM, and deep JWT security testing. Covers XML signature wrapping (XSW1-8), ds:Signature stripping and comment-injection (canonicalization) attacks, signature-exclusion / unsigned-assertion acceptance, golden SAML (forged assertions from a stolen IdP signing key), IdP-initiated SSO abuse and unsolicited-response replay, SAML assertion XXE, RelayState open-redirect/injection, and audience/recipient/NotOnOrAfter validation gaps. Plus SCIM provisioning abuse: JIT auto-provisioning role injection, active=true reactivation, PATCH privilege escalation, and cross-tenant user creation. And deep JWT: alg confusion (RS256 to HS256), alg:none, kid SQL/path-traversal injection, jku/x5u header SSRF, embedded jwk header key injection, and weak-secret brute force. Uses jwt_tool, xmllint, python, and manual http payloads. Chains from /pentester or /web-exploit; into /post-exploit and /cloud-identity-federation on takeover or federated-role access.

Cloud security posture assessment for AWS, Azure, and GCP. Tests IAM privilege escalation paths, public storage exposure, serverless attack surface, database exposure, logging gaps, container registry security, and cloud-specific attacks. Both authenticated (with cloud credentials) and unauthenticated (external) modes. Uses nuclei cloud templates, Prowler, ScoutSuite, manual IMDS/metadata probing, and deep AWS/Azure/GCP CLI enumeration. Produces: cloud architecture diagram, attack path map, findings per category, compliance mapping (SOC 2, PCI DSS 4.0, HIPAA, CIS), PoCs for confirmed exploits. Chains into /gh-export for issue filing.

Deep OSINT reconnaissance using the MITRE ATT&CK Reconnaissance framework. Email harvesting with SMTP verification, subdomain takeover detection, certificate transparency mining, Shodan/Censys intelligence, Wayback Machine historical analysis, social media profiling, cloud storage enumeration, document metadata extraction, DNS history, credential leak checks, and passive infrastructure mapping. Uses theHarvester, amass, dnsrecon, fierce, dnstwist, dmitry, whatweb, wafw00f, exiftool, metagoofil, smtp-user-enum, swaks, waybackurls, subfinder, and crt.sh. Pure reconnaissance — no active exploitation. Produces: confidence-scored findings, infrastructure diagram, employee roster, email pattern confirmation, subdomain takeover candidates. Chains into /pentester for active testing.

Systematic fuzzing across two dimensions: (1) content discovery — hidden directories, files, backup/source leaks, HTTP verb enumeration, 401/403 bypass via path manipulation; (2) input validation — auth/token stripping, type confusion, boundary value analysis, HTTP parameter pollution, header fuzzing, cookie fuzzing, mass assignment discovery, and entropy/predictability analysis of any generated value. Works on any domain. Chains from /web-exploit or /pentester; chains into /business-logic when boundary violations, predictable IDs, or mass assignment are confirmed.

AI/LLM red-team assessment using OWASP LLM Top 10 (2025), the OWASP AI Testing Guide (AITG v1, Nov 2025), and OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, and MCP command injection. Combines four tools: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based scanning), and promptfoo (plugin-based red-team eval) - each covering different OWASP categories. Includes a conditional MCP recon phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces an OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, an architecture diagram, and PoCs. Chains into /gh-export.

Analyzes CVE vulnerabilities in project dependencies with code path tracing and PoC generation for Burp Suite. Traces vulnerable code from user input to sink, assesses exploitability, and generates HTTP requests for testing.

Generates specific, implementable fixes for every finding in findings.json. Produces code patches (unified diff), configuration changes, dependency updates, and IaC fixes — not generic advice but actual before/after code. Uses the reproduction command from each finding as the verification step: "run this after the fix — it should now fail." Stores remediation data in findings.json so the dashboard shows a Fix button and /gh-export includes the remediation in GitHub issues. Chains from /pentester, /codebase, or any scan skill after findings are produced. Chains into /gh-export for export with remediation included.

Structured threat modeling skill using the PASTA framework (Process for Attack Simulation and Threat Analysis) combined with Adam Shostack's 4-question framework. Use this skill whenever the user asks to do threat modeling, security analysis, map the attack surface, identify threats, or review an application for security risks — even if they don't mention PASTA or a specific framework by name. Core activities: Component Mapping (architecture + data flows), Critical Assessment (business impact prioritization), and Logic Flaw Identification (attacker mindset on business logic). Produces: component map diagram (Mermaid), data flow diagram (Mermaid), attack tree (Mermaid), STRIDE threat table, prioritized risk register, and an actionable mitigation plan. Invoke proactively for any security review, architecture review, or "what could go wrong?" session.

Container and Kubernetes security assessment. Tests container escape vectors, Docker/containerd socket exposure, K8s RBAC misconfigurations, pod security violations, exposed API servers, etcd access, service account token abuse, image layer secrets, private registry attacks, SSRF to metadata services, cross-namespace network bypass, CIS benchmarks, crypto miner detection, resource exhaustion, and admission controller gaps. Both external and internal (compromised pod) perspectives. Uses trivy, kube-bench, kubectl, nuclei, dive, amicontained, and docker-bench-security. Covers OWASP Kubernetes Top 10 and all 22 Kubernetes Goat attack scenarios.

Android app security assessment structured on OWASP MASVS 2.0 / MASTG. Static analysis of an APK (MobSF, jadx, apktool, dex2jar, mobsfscan): hardcoded secrets, weak/broken crypto, insecure data storage, exported activities/services/providers/receivers, android:allowBackup, cleartext traffic & network-security-config, WebView addJavascriptInterface bridges, insecure deeplinks/intent redirection, missing FLAG_SECURE, tapjacking, root/anti-Frida detection, vulnerable third-party SDKs, Firebase/cloud-config leaks. Dynamic analysis (opt-in, needs a device) via Frida/objection: SSL-pinning bypass, runtime keystore/shared-prefs/SQLite dumps, traffic capture, deeplink & IPC abuse. Chains from /pentester and /codebase; into /api-security for backend endpoints, /web-exploit for injection, /post-exploit on device RCE, /ai-redteam on an embedded LLM.

iOS app security assessment structured on OWASP MASVS 2.0 / MASTG. Static analysis of an IPA (MobSF, class-dump, otool/nm, mobsfscan): hardcoded secrets, weak/broken crypto, insecure data storage (NSUserDefaults, plists, Core Data, Keychain accessibility), Info.plist misconfig, ATS (App Transport Security) exceptions & missing cert pinning, custom URL-scheme hijacking, Universal Link validation, UIPasteboard leakage, screenshot/snapshot caching, WKWebView JS bridges, missing jailbreak/anti-debug detection, vulnerable third-party pods/frameworks. Dynamic analysis (opt-in, needs a JAILBROKEN device — cannot be containerized) via Frida/objection: SSL-pinning bypass, Keychain dumps, runtime storage inspection, URL-scheme & pasteboard abuse. Chains from /pentester and /codebase; into /api-security for backend endpoints, /web-exploit for injection, /post-exploit on device access, /ai-redteam on an embedded LLM.

Generate an OWASP MASVS 2.0 compliance matrix for a mobile app, mapped to MASTG test IDs and tagged by NowSecure risk tier. Produces a control-by-control table across all 8 MASVS groups (STORAGE, CRYPTO, AUTH, NETWORK, PLATFORM, CODE, RESILIENCE, PRIVACY) with a constrained status enum (compliant / non_compliant / not_applicable / needs_dynamic), file:line evidence per control, and an anti-overclaim rule (a control needing runtime proof cannot be marked compliant on static evidence alone). The mobile analog of /compliance (which covers ASVS). Chains from /mobile-pentest-plan, /android-security, /ios-security to turn their findings into an audit-grade deliverable.

Mobile pentest orchestrator & scoping front-end. Given a mobile app (APK, IPA, source tree, package name / bundle id) — especially when you don't yet know the platform or the app ships BOTH Android and iOS builds — fingerprint it (native vs React-Native/Flutter/Xamarin/Cordova, build flavor, signing, SDK inventory, endpoints, attack surface), classify data sensitivity into a NowSecure Tier (1/2/3), derive the mandatory OWASP MASVS 2.0 control baseline + test depth for that tier, produce a scoped MASTG-based pentest plan, then dispatch to /android-security and/or /ios-security to execute. The mobile analog of /pentester. Chains into /masvs-checklist for the compliance matrix and /api-security for discovered backends.

Active Directory security audit using the MITRE ATT&CK framework. Full domain enumeration, trust mapping, GPO analysis, ACL abuse paths, ADCS attacks (ESC1-ESC8), delegation abuse (constrained/unconstrained/RBCD), fine-grained password policies, LAPS deployment, service account security, and Kerberos configuration. Uses enum4linux-ng, netexec, impacket, ldapsearch, certipy-ad, bloodhound-python, and rpcclient. Produces attack path diagrams, prioritized risk register, and PoCs. Chains into /gh-export for issue filing.

Authentication and credential security assessment. Tests password brute-force, credential stuffing, password spraying, default credential testing, credential harvesting, lockout analysis, MFA bypass, OAuth/OIDC abuse, session token entropy, Kerberos attacks, and intelligent wordlist generation. Uses hydra, john, ncrack, medusa, cewl, crunch, netexec, impacket, kerbrute, and nuclei default-login templates. Covers OWASP A07:2021 Identification and Authentication Failures.

Email infrastructure security audit. Tests SPF, DKIM, DMARC configuration, open relay, email spoofing resilience, S/MIME, MTA-STS, TLS-RPT, and SMTP security. Uses swaks, dnsrecon, nmap SMTP scripts, smtp-user-enum, and dig. Pure skill markdown — no new infrastructure needed.

Active Directory and network lateral movement assessment. Pass-the-hash, pass-the-ticket, Kerberoasting, AS-REP roasting, NTLM relay, SMB relay, WMI/WinRM/PSRemoting abuse, constrained/unconstrained delegation, RBCD, cross-trust exploitation, and pivoting. Uses impacket, netexec, enum4linux-ng, smbmap, smbclient, bloodhound-python, Responder, ntlmrelayx, mitm6, and ldap-utils. Chains from /post-exploit or /credential-audit.

Exploit validation and exploitation using Metasploit Framework. Runs in a dedicated Docker container (separate from Kali). Validates CVEs discovered by nuclei, nikto, or other scanners with actual exploit modules. Covers exploit selection, payload configuration, exploitation, and post-exploitation pivoting. Uses msfconsole, msfvenom, and the Metasploit module database. Chains from /pentester, /analyze-cve, or /post-exploit when exploitable CVEs are confirmed.

Internal network assessment. VLAN hopping, ARP spoofing detection, broadcast protocol abuse (LLMNR/NBT-NS/mDNS), network segmentation verification, SNMP enumeration, NFS exposure, router/switch audit, and internal service mapping. Assumes attacker has network access. Uses nmap, arp-scan, nbtscan, snmpwalk, onesixtyone, smbmap, nfs-common, masscan, hping3, and netexec.

TLS/SSL configuration audit. Tests protocol versions (SSLv2/3, TLS 1.0/1.1/1.2/1.3), cipher strength and ordering, certificate chain validation (intermediates, CT logs, OCSP stapling, pinning), known vulnerabilities (POODLE, BEAST, CRIME, Heartbleed, ROBOT, DROWN, Ticketbleed, GOLDENDOODLE), session management (ticket reuse, resumption, fixation), renegotiation attacks, TLS 1.3-specific issues (0-RTT replay, PSK modes, downgrade), HSTS deep analysis (preload, subdomains, bypass), and certificate revocation (CRL, OCSP responder, stapled response freshness). Compliance-mapped to PCI DSS 4.0 (full Section 4), NIST SP 800-52r2, and FedRAMP. Uses testssl.sh, sslscan, sslyze, openssl, nmap NSE scripts, and nuclei SSL templates. Multi-port scanning across 20+ TLS-bearing services.

Deep API security assessment beyond surface scanning, covering the full OWASP API Security Top 10 (2023): Broken Object Level Authorization (BOLA/IDOR), Broken Authentication, Broken Object Property Level Authorization (mass assignment + excessive data exposure), Unrestricted Resource Consumption, Broken Function Level Authorization (BFLA), Unrestricted Access to Sensitive Business Flows, SSRF via API parameters, Security Misconfiguration, Improper Inventory Management (shadow/zombie/deprecated endpoints, v1/v2 drift), and Unsafe Consumption of third-party APIs. Works across REST, GraphQL, gRPC, SOAP, and MCP servers. Discovers APIs from OpenAPI/Swagger, GraphQL introspection, gRPC reflection, .well-known, and traffic capture. Uses kiterunner, ffuf, schemathesis, openapi-fuzzer, graphql-cop, inql, jwt_tool, and mitmproxy with real payloads. Chains from /pentester or /codebase, into /web-exploit for injection points, /post-exploit on RCE, and /ai-redteam when an LLM/AI endpoint is found.

Deep OAuth 2.0 / OpenID Connect security assessment covering the full attack surface: redirect_uri validation bypass (path traversal, open redirect chains, subdomain confusion, parameter pollution, response mode switching), missing/broken state CSRF, PKCE downgrade and absent-challenge attacks, implicit grant token leakage, authorization code injection, scope escalation, client confusion, mutable-claims account takeover (iss+sub confusion, email-keyed identity merging), pre-account takeover, OIDC dynamic client registration SSRF (logo_uri, jwks_uri, request_uri), nonce replay, ID token validation failures, Device Code phishing, mobile custom URI scheme hijacking, refresh token persistence, consent screen clickjacking, host header injection, and cross-IdP mix-up attacks. Uses KOAuth, jwt_tool, nuclei oauth templates, and manual http payloads with verification logic. Chains from /pentester or /api-security; into /web-exploit, /post-exploit on account takeover, and /credential-audit when tokens are recovered.

Triages an Aikido security findings CSV against a local codebase. For each finding, reads the flagged file, traces the code path, and verdicts it as KEEP OPEN or CLOSE with a specific reason. Outputs a reviewed CSV and a self-contained HTML evidence report. Run this at the end of a pentest when an Aikido CSV is available.

Full ASVS 5.0 compliance assessment against a codebase and/or architecture diagrams. Reads all 346 controls from the companion CSV, performs targeted code analysis per control, and produces a complete matrix marked COMPLIANT / NON_COMPLIANT / NOT_RELEVANT — with per-control reasoning and evidence (code snippets, file:line references, diagram observations). Outputs a reviewed CSV matrix and a self-contained HTML evidence report.

Generates CVE request packages from pentest findings. Reads cve-candidates.json (auto-generated at pentest completion) or findings.json directly, then produces for each qualifying vulnerability: MITRE CVE form data, GitHub Security Advisory draft, full disclosure report, and vendor notification email. Invoke manually after a pentest engagement when you have true-positive findings that warrant CVE IDs.

Application-level business logic security testing for any domain. Takes an understanding-first approach: map the intended workflows before probing them. Covers: value/quantity logic abuse (negative, zero, overflow, rounding on any numeric field), workflow and state machine bypass (skipping required steps, forcing illegal state transitions, reusing one-time tokens), trust boundary violations (BOLA horizontal/vertical, BFLA, cross-tenant access, negative ownership attacks), idempotency and replay attacks (duplicate submissions, double-spend, same-reference reuse), multi-step flow integrity (checkout, registration, approval, verification), quota and rate limit bypass, time/date manipulation, and authorization code / reference number predictability. Domain-agnostic — applies to SaaS, e-commerce, banking, gaming, social platforms, APIs, or any multi-user application with stateful workflows. Chains from /pentester; chains into /param-fuzz when boundary violations or mass assignment are confirmed.

Full penetration test using MCP tools — recon, scanning, exploitation, and reporting. Tailored for OpenCode (BYO LLM). Supports network/web targets and local codebases. Chains into analyze-cve, threat-modeling, and remediate skills automatically.