Offensive AI security testing and exploitation framework. Systematically tests LLM applications for OWASP Top 10 vulnerabilities including prompt injection, model extraction, data poisoning, and supply chain attacks. Integrates with pentest workflows to discover and exploit AI-specific threats.

API security testing - GraphQL, REST API, WebSocket, and Web-LLM attack techniques.

Stitches confirmed single-asset findings into multi-hop attack paths across the organization. Builds a graph where nodes are assets and edges are confirmed exploit hops citing the findings that enable them.

Acquire an authenticated session THROUGH MFA/OTP on an in-scope target and emit a reusable session artifact (Playwright storageState + Bearer) so executors can test the post-auth attack surface. Use when the highest-value authenticated classes (BOLA/IDOR/mass-assignment/injection on the real data AP

Authentication security testing - auth bypass, JWT attacks, OAuth flaws, password attacks, 2FA bypass, CAPTCHA bypass, and bot detection evasion.

Smart contract security testing and blockchain CTF exploitation. Covers Solidity vulnerability analysis, EVM storage manipulation, delegatecall attacks, CREATE/CREATE2 address prediction, and common DeFi exploit patterns. Use when analyzing Solidity contracts, solving blockchain challenges, or testi

Client-side vulnerability testing - XSS (reflected/stored/DOM), CSRF, CORS misconfiguration, Clickjacking, DOM-based attacks, and Prototype Pollution.

Cloud and container security testing - AWS, Azure, GCP, Docker, and Kubernetes misconfigurations and exploitation.

Detect and break the cloud post-compromise attack chain (AWS / Azure / GCP) — per-stage CloudTrail / Activity-Log / Audit-Log detection signals and the preventive controls that close each step. Use for cloud detection engineering, hardening, remediation write-ups, or blue-team posture review of the

Pentest coordination — orchestrates executor and validator agents with context-controlled spawning. Entry point for all engagements.

Cryptanalysis techniques — lattice attacks, padding oracles, weak-RNG exploitation, signature forgery, secret-sharing recovery.

CVE research, standalone PoC script and report generation. Given a CVE ID, researches NVD and advisories, generates a safe Python PoC, and writes a detailed vulnerability report.

Retrieve CVE risk scores from NVD. Auto-invoked whenever a CVE ID is mentioned to display CVSS score, severity, CWE, and description.

Digital forensics and incident response - Windows event log analysis, PCAP forensics, filesystem artifact analysis, AD attack detection, and timeline correlation. Use when investigating security incidents, analyzing Sherlocks, or performing threat hunting on provided evidence files.

Core pentesting tools and methodology - Burp Suite usage, Playwright automation, binary analysis, testing methodology, and professional reporting standards.

Evidence-safe firewall ruleset audit reference specification — 22 documented detector patterns (17 vendor-agnostic plus 5 FortiGate-specific), a 15-check semantic catalogue, CIS Fortinet FortiGate Benchmark guidance, a custom customer-policy benchmark, and consolidated network-team Excel profiles in

GitHub workflow automation — branching, committing, pushing, pull requests, issues, and code review. Use when asked to commit, push, create PRs/branches/issues, or manage git workflow.

HackerOne bug bounty automation - parses scope CSVs, deploys parallel pentesting agents per asset, validates PoCs, and generates platform-ready submission reports.

HackTheBox platform operations and automations to solve challenges, machines and capture the flags hacking competitions

Network infrastructure testing - port scanning, DNS attacks, MITM, VLAN hopping, IPv6, SMB/NetBIOS, sniffing, and DoS assessment.

Injection vulnerability testing - SQL, NoSQL, OS Command, SSTI, XXE, and LDAP/XPath injection techniques.

Mobile application security testing (Android + iOS) mapped to OWASP MASVS/MASTG — static reversing (Flutter AOT, Unity IL2CPP, React Native/Hermes, native ARM64, Mach-O/Swift), SAST (manifest/IPC, storage, crypto, signing), dynamic analysis (Frida/objection, TLS-pinning + root/jailbreak bypass, traf

Offensive testing of perimeter network appliances and VPN crypto — IKE/IPsec (aggressive-mode, transform/DH enum, NAT-T), Check Point SIC/OPSEC, safe firmware/patch-level inference for FortiGate/PAN-OS/Cisco ASA/Citrix feeding CVE applicability, NTLM Type-2 target-info decode, handshake-completion T

Open-source intelligence gathering - company repository enumeration, secret scanning, git history analysis, employee footprint, and code exposure discovery.

Fetches and extracts payloads from PayloadsAllTheThings on demand. Bake into executor prompts for live payload enrichment.

Automated PCI Secure Software Standard (SSS) v2.0 readiness gap-assessment of an application from its source code and documentation. Deterministically enumerates every applicable Test Requirement from a pinned catalog, gathers source/doc evidence, and emits an evidence-bound per-requirement verdict

Run a professional penetration engagement OR a network vulnerability scan from a scope. WEB mode (apex domains / app URLs) — mandatory surface expansion, systematic OWASP attack-class coverage, reversible active exploitation, authoritative validation, Transilience PDF. NETWORK mode (a list of IPs/CI

Generate ONE strong password and apply it to each referenced file (PDF, Word, Excel, PowerPoint, or any type). Use when asked to password-protect / encrypt / lock one or more deliverable files with a single password before sharing.

Domain assessment and web application mapping - subdomain discovery, port scanning, endpoint enumeration, API discovery, and attack surface analysis.

Re-validates every previously-confirmed finding against its current target — detects drift (patched, mitigated, re-introduced). Cron-driven weekly sweep across the org's validated finding tree.

Static and dynamic reverse engineering — ELF/PE analysis, custom-VM bytecode, packed binaries, anti-debug bypass, Frida hooking.

Risk-based prioritisation of confirmed attack paths. Combines exploit feasibility, technical CVSS severity, and asset business impact into a single ranked list driving remediation roadmaps.

Generates optimized, syntax-validated scripts on demand. Never executes — only generates, optimizes, and validates.

Server-side vulnerability testing - SSRF, HTTP Request Smuggling, Path Traversal, File Upload, Insecure Deserialization, and Host Header injection.

Identify and remove negative-ROI skill content — orphan files, never-read entries, duplicates, content reintroducing challenge-specific lore. Inverse of /skill-update. Use during quarterly maintenance or after the linter flags issues.

Skill creation, update and management — generates skill directory structure, validates against best practices, enforces line count limits. Use when creating, updating, or improving skills.

Social engineering testing - phishing, pretexting, vishing, and physical security assessment techniques.

Security-focused source code review and SAST. Scans for vulnerabilities (OWASP Top 10, CWE Top 25), CVEs in third-party dependencies/packages, hardcoded secrets, malicious code, and insecure patterns. Use when given source code, a repo path, or asked to "audit", "scan", "review" code security, or "c

System exploitation testing - Active Directory attacks, privilege escalation (Linux/Windows), and exploit development.

OSINT-based technology stack identification. Routes to 6 domain sub-skills (frontend, backend, infra, security, osint, correlation) to discover a target's stack from publicly available signals.

Threat-intel signal ingest — converts a CVE + affected-asset + claim payload into a queued engagement-scope row for the validation pipeline.

Generate a Transilience-branded PDF report (pentest, vuln assessment, compliance, threat intel) from a single findings JSON using the bundled ReportLab generator. Use whenever an engagement needs its final report/deliverable PDF in Transilience house style.

Web application logic testing - business logic flaws, race conditions, access control, cache poisoning/deception, and information disclosure.

Business-impact gate. Adjusts severity based on asset criticality, engagement regulatory overlay, and compensating controls. Does NOT veto findings.

Deterministic (not LLM). Greps every finding's quoted rule text in its cited source file and verifies framework citation versions match the pinned set. Mismatches → quarantine.

Technical truth gate. Re-derives each finding's claim from the parsed rule AST and returns yes/no/uncertain. Uncertain findings route to held/ for human reviewer.

Editorial gate. Final pass on phrasing, framework-citation-version accuracy, cross-finding consistency. Flags (never blocks) findings that need author attention.

20+ year offensive security reviewer. Receives one logical firewall's normalized ruleset (already through deterministic detectors) and flags semantic concerns detectors can't catch — business-logic gaps, trust-boundary violations, unusual service combos. 2-4 instances dispatched in parallel during /

Dispatch brief for the citation-verifier step — runs the deterministic, non-LLM grep gate (tools/pci-sss/citation_verify.py) over every PCI SSS v2.0 verdict's cited evidence and quarantines any that cannot be confirmed. The verifier is code, not judgement; this brief governs how an agent invokes it

Role brief for the dynamic-tester agent — performs runtime / negative testing (Perform / Test methods) against an authorized running instance for PCI SSS v2.0 dynamic Test Requirements, capturing dynamic_observation evidence. When no running instance is authorized, the requirement is REQUIRES_MANUAL

Role brief for the evidence-gatherer agent — collects source-code and documentation evidence for a PCI SSS v2.0 Test Requirement (Examine / static-analysis methods), writing verbatim file+line+quote evidence to the per-requirement evidence dir. Mounted by the workflow Gather phase.

Role brief for the blind refutation-validator agent — independently tries to disprove a proposed MET/NOT_MET PCI SSS v2.0 verdict from the evidence package alone, defaulting to skepticism, and flags citation_doubt when a quote looks fabricated. N run in parallel per requirement; a majority refute ki

Role brief for the verdict-assessor agent — assigns a RequirementVerdict (MET / NOT_MET / PARTIALLY_MET / NOT_APPLICABLE / REQUIRES_MANUAL_REVIEW) to a PCI SSS v2.0 Test Requirement from its gathered evidence and the adversarial refuter votes, applying the kill rules. Mounted by the workflow Assess/

Parse all configs in the current engagement, dispatch senior-pentester subagents in parallel, run the validation chain, emit findings ready for /review.

Curator commands for learning-loop candidates. Usage — /pending list | /pending review <id> | /pending promote <id> | /pending reject <id> | /pending hold <id>

Create a program report or annual report with your organization's branding

Name also used by claude-skills-journalism

Run the altimate-code dbt/SQL PR reviewer on the current diff, PR, or commit and present the signed verdict verbatim.

Name also used by altimate-code, claude-skills-journalism

Start a new firewall-review engagement. Argus greets the operator, asks all six scoping questions in one batch, scaffolds the engagement folder, and waits for configs. No arguments.