Claude Skills by brucesongs

Advanced 5G/6G telecom attacks covering 5G Core (SBA) exploitation, IMSI catcher evolution (5G Stingray), SIP/Diameter protocol attacks, Open RAN vulnerabilities, network slicing abuse, and early 6G research vectors (THz comms, AI-native air interface).

5G core (AMF/SMF/UPF), RAN, signaling (PFCP/GTP/Diameter/SS7), IMSI catchers, O-RAN security, roaming abuse, SMS interception, and telecom infrastructure red team operations.

Active Directory Certificate Services (AD CS) abuse — ESC1-ESC15 attack patterns, PKINIT, PetitPotam to AD CS to Domain Admin chains, CVE-2022-26923 (Certifried), Shadow Credentials, Golden Certificate, certificate template ACL abuse, NTLM relay to web enrollment.

Active Directory is the backbone of enterprise identity and access management, making it a primary target during internal network penetration tests.

LLM-driven autonomous penetration testing framework operations covering PentestGPT, HexStrike AI, Viper, PentestAgent, AI-Infra-Guard, AutoPWN, and custom agent harness patterns — including reasoning chain orchestration, tool delegation, context window management, output validation, multi-agent pentest team coordination, and human-in-the-loop checkpoints.

AI agent framework attack surface — orchestration-layer compromise of LangChain (Python/JS), LangGraph, CrewAI, Microsoft AutoGen, OpenAI Assistants API v2, Anthropic Claude Agent SDK, LlamaIndex, Microsoft Semantic Kernel, Google ADK, SmolAgents, and MCP-integrated agent runtimes. Covers tool poisoning (Simon Willison 2025 research), indirect prompt injection via untrusted tool outputs, tool rug-pull attacks (npm/PyPI dependency confusion in agent toolkits), LangChain SSRF via RequestsTool /...

Offensive security testing of AI agent systems covering MCP server attacks, tool poisoning, indirect prompt injection against agents, RAG knowledge base poisoning, agent sandbox escape, multi-agent compromise chains, and autonomous agent hijacking — using MCP security testers, HexStrike AI, AI-Infra-Guard, custom agent harness probes, and prompt injection toolkits.

AI/ML supply chain attacks — model poisoning, Pickle RCE, Hugging Face / Ollama registry compromise, LangChain plugin backdoors, OpenClaw / ClawHub ecosystem threats. Distinguishes from ci-cd-supply-chain-attack by focusing on model weights, training data, and serialization formats. Anchored by the 2026-07 Hugging Face incident (the 'Chernobyl moment' of software supply chain security).

AI-assisted fuzzing for automated vulnerability discovery. Coverage-guided fuzzing engines, AI-driven seed generation, intelligent mutation strategies, and systematic crash triage.

Advanced AI safety red team operations covering OWASP LLM Top 10 (2025), prompt injection (direct/indirect/multi-turn), jailbreak techniques (DAN, cognitive hacking, persona-based), data poisoning detection, model inversion attacks, adversarial examples (evasion), model extraction, and AI supply chain attacks against LLM-integrated applications, agent frameworks, and RAG systems.

Semantic-layer attack testing against AI systems and LLM-integrated applications.

Anti-forensics is the offensive counterpart to digital forensics.

API Security Testing covers security assessment across three major API architectures: REST, GraphQL, and gRPC, focusing on the OWASP API Security Top 10 core risks: Broken Authentication, Broken Object Level Authorization (BOLA), Excessive Data Exposure, Rate Limiting Bypass.

Transform technical findings into clear, structured written content: penetration test reports, vulnerability disclosures, security blog posts, and technical documentation.

CAN/CAN-FD bus analysis, UDS diagnostics, IVI pentest, OBD-II exploitation, key fob replay/relay attacks, GNSS spoofing, EV charging station (ISO 15118), and connected vehicle red team operations.

Performing repetitive enumeration across many targets - Running batch vulnerability scans on multiple hosts - Monitoring for changes in target environment - Executing attack chains that require iterative steps - User says \"loop\", \"automate\", \"batch\", \"repeat.

AV/EDR evasion covers techniques for bypassing antivirus (AV) and Endpoint Detection/Response (EDR) solutions during payload delivery, execution, and post-exploitation.

Binary reverse engineering covers the complete chain from static analysis, dynamic debugging, to vulnerability discovery, exploit development, and malware analysis.

Layer-2 blockchain attack — Lightning Network (BOLT, HTLC), Optimistic Rollups (Optimism/Arbitrum/Boba/Base), ZK Rollups (zkSync/StarkNet/Polygon zkEVM/Scroll/Linea), Polygon PoS, Gnosis sidechain, cross-chain bridges (Wormhole/Nomad/Ronin/Poly Network/Multichain/Horizon), state channels, ERC-4337 account abstraction, and DA layers (Celestia/EigenDA/Avail).

Blockchain & Web3 security — Solidity/Vyper smart contract auditing, DeFi attack vectors (flash loans, MEV, oracle manipulation), bridge attacks, wallet security, with tooling from Slither/Mythril/Foundry.

Near-field wireless penetration testing skills covering Bluetooth Classic device enumeration and exploitation, BLE GATT service attacks against IoT devices, RFID card cloning (MIFARE Classic/DESFire), NFC tag manipulation, and contactless payment probing.

Automated browser-based security testing using Playwright and browser devtools. Interact with web applications as a user would — click, type, navigate — while monitoring network traffic, JavaScript execution, and DOM changes for security issues.

A system for recording, indexing, and distilling knowledge from agent lifecycle events. Through a three-layer document system (overview -> detailed records -> knowledge distillation), raw conversation events are transformed into reusable experience.

CI/CD pipeline and software supply chain compromise covering Jenkins (script console, Jenkinsfile injection, shared library abuse, CVE-2024-23897 args4j), GitLab CI/CD (runner abuse, .gitlab-ci.yml injection, self-hosted runner takeover, CVE-2022-1162, OmniAuth CVE-2024-9653), GitHub Actions (self-hosted runner abuse, pull_request_target trap, workflow injection via issue/PR title, secrets exfiltration via cache/artifact, GITHUB_TOKEN scope), CircleCI (context theft, OIDC abuse), Argo CD (CVE...

Cloud identity provider attacks covering Azure AD/Entra ID, Okta, Auth0, Ping, AWS IAM Identity Center, and Google Workspace — including OAuth 2.0 token theft, OIDC redirect abuse, SAML response forgery, conditional access bypass, MFA fatigue, federation compromise (AD FS, Ping), app registration abuse, and JIT access exploitation using ROADtools, AADInternals, MicroBurst, MFASweep, TokenTactics, and Okta API probing tools.

CVE research methodology, PoC reproduction, patch gap analysis, and exploit chain composition across container/k8s/cloud-native surfaces; SBOM-driven vuln management and nuclei template authoring.

Cloud security covers security assessment for major cloud platforms including AWS, Azure, and GCP, with core focus on IAM misconfiguration detection, storage bucket exposure scanning, metadata service attacks, container escape, and Kubernetes RBAC auditing.

Targeted security assessment of Content Management Systems (WordPress, Joomla, Drupal) using specialized scanners and exploit techniques.

Rapidly acquire a mental model of any unfamiliar codebase — from a 500-line script to a 100M+ line monorepo. This skill transforms raw code into structured intelligence: architecture maps, entry points, data flows, security surfaces, and onboarding confidence scores.

Advanced injection attacks beyond SQL - covering OS command injection, LDAP injection, NoSQL injection, template injection (SSTI), XPath injection, and comprehensive filter bypass techniques.

Concurrency exploitation covers race condition vulnerabilities including TOCTOU, signal handler races, thread synchronization bypasses, and timing attacks.

Attacks against Trusted Execution Environments (TEEs) and confidential computing platforms — Intel SGX (Foreshadow/SGAxe/LVI/ÆPIC Leak), Intel TDX, AMD SEV/SEV-ES/SEV-SNP (CrossLine/BadRAM), Azure CCF, Marblerun, and Gramine/Occlum libos enclaves. Covers side-channel leakage, attestation forgery, ABI misuse, host-to-enclave breakout, enclave-to-host escape, and recovery of sealed secrets. Distinct from hardware-security (broad hardware attacks) and firmware-reverse (UEFI/BIOS).

Container security covers the complete lifecycle from image building, registry management, runtime protection, to orchestration platform (Kubernetes) security.

After completing a penetration test engagement - When encountering a novel attack technique or defense - After a tool produces unexpected results - When identifying recurring patterns across targets - User says \"learn\", \"remember this\", \"pattern.

Council provides a structured framework for analyzing security questions from multiple adversarial and defensive perspectives simultaneously.

Cyber-Physical Systems (CPS) attacks — PLCs (Siemens S7, Rockwell ControlLogix, Schneider Modicon, Mitsubishi MELSEC), ICS protocols (Modbus, DNP3, Profinet, EtherNet/IP, IEC 61850, OPC UA), HMIs, SCADA historians, OT-to-IT pivot, SIS bypass. Distinct from scada-ics-security (broader ICS overview) — this skill goes deep on protocol-level PLC exploitation, packet replay/injection, and field-device firmware attacks. Covers 2024-2025 incidents (Unitronics PLC attack, Pipedream/Incontroller, mult...

Cryptographic Attacks target implementation flaws and algorithm weaknesses in encryption systems, covering OWASP A04: Cryptographic Failures.

CSPM/CASB/CNAPP platform bypass and abuse — rule suppression exploitation, IaC state manipulation, CASB proxy evasion, SaaS shadow discovery, Wiz/Prisma/Lacework/Defender coverage gap identification, and tag-tampering attacks against cloud posture management tools.

Dark web intelligence gathering — Tor/onion service reconnaissance, marketplace monitoring, breach data markets, threat actor profiling, with strict OPSEC for investigators.

Attacks for exfiltrating data from compromised networks and bypassing DLP/egress controls. Covers DNS tunneling, ICMP/HTTPS tunneling, protocol smuggling, steganographic exfil, cloud-native exfil (S3/OpenSearch/BigQuery), and DLP bypass. Use when testing egress monitoring, validating DLP controls, or simulating APT exfiltration campaigns.

DLP bypass techniques covering steganography (LSB, audio, video), DNS tunneling, ICMP tunneling, cloud sync abuse (Dropbox, OneDrive), WebSocket/HTTP3 exfil, AI-augmented exfil (semantic chunking), and modern DLP evasion patterns.

Attacks against cloud data platforms and analytics pipelines — Snowflake, Databricks, BigQuery, Redshift, dbt, Apache Airflow, and lakehouse architectures. Covers identity-based breaches (no perimeter), warehouse SQL injection at scale, IAM privilege escalation, secrets in DAGs, notebook code injection, and cross-tenant data exfiltration. Distinct from database-attack (protocol-level RDBMS) and cloud-security (broader CSP control plane).

Automated data collection from structured sources: CVE databases, threat intelligence feeds, exploit databases, and security advisories. Transform unstructured web data into structured knowledge units.

Direct attacks against database servers at the protocol level — distinct from web-based SQL injection (covered by web-sqli). This skill targets database listeners, authentication mechanisms, stored procedures, and protocol-level misconfigurations.

Defensive deception and honeypot deployment covering SSH/Telnet (Cowrie), web (OpenCanary), enterprise (HFish), ICS/SCADA (Conpot), all-in-one (T-Pot), AI-driven deception (Beelzebub), Thinkst Canarytokens (DNS, HTTP, file, AWS API key, SQL), Dionaea multi-protocol honeypot, notification pipelines (Slack/Teams webhooks), false positive tuning, and attacker engagement — including lure design, deployment OPSEC, IOC extraction, and attacker attribution.

Multi-source intelligence gathering through systematic web research — producing thorough, cited reports from diverse sources.

Detection-as-code engineering covering Sigma rule authoring, YARA signature development, Splunk SPL / Kusto KQL / Elastic EQL queries, MITRE ATT&CK mapping, detection CI/CD pipelines, false-positive tuning, and rule testing against EVTX-ATTACK-SAMPLES — using SigmaHQ, Yara-Rules, Loki, yarGen, hayabusa, SigmaCLI, and zircollo.

Digital forensics covers the complete workflow of disk forensics, memory forensics, network forensics, file recovery/carving, and chain of custody.

DNS Attacks exploit the Domain Name System protocol for reconnaissance, spoofing, tunneling, and data exfiltration. DNS is a foundational infrastructure service that is frequently misconfigured, poorly monitored, and trusted by default -- making it an ideal attack vector.

Setting up a practice lab for penetration testing techniques - Creating isolated environments for exploit development and testing - Building vulnerable application targets for training - Testing tools against known-vulnerable configurations - User says \"lab\", \"docker lab.