Agent skills for OpenAI Agents SDK

Executes Atomic Red Team tests mapped to MITRE ATT&CK via Invoke-AtomicRedTeam

Plans and facilitates tabletop exercises simulating ransomware incidents,

This skill empowers Claude to perform regression analysis and modeling using the regression-analysis-tool plugin.

Perform security analysis of Siemens S7comm and S7CommPlus protocols

Audit service accounts across enterprise infrastructure to identify orphaned,

Automates credential rotation for service accounts across Active Directory,

Simulates SSL stripping / HTTPS downgrade attacks using sslstrip, Bettercap, and mitmproxy in authorized lab environments to test HSTS…

Enumerate subdomains of target domains using ProjectDiscovery's Subfinder

Simulates and detects software supply chain attacks: typosquatting detection via Levenshtein distance against popular PyPI package names…

Simulates VLAN hopping attacks using switch spoofing and 802.1Q double tagging techniques in authorized lab environments to test VLAN…

Performs authenticated and unauthenticated vulnerability scanning using

Executes web cache deception attacks by exploiting path normalization

Captures WPA/WPA2 handshakes and performs offline password cracking

Execute a wireless network penetration test to assess WiFi security by

Develops precise YARA and YARA-X rules for malware detection by identifying

Automate Perigon tasks via Rube MCP (Composio).

Design a lesson that embeds PERMA wellbeing elements alongside academic learning objectives.

Organizes and sorts permission allowlists for AI agents, tools, and services hierarchically without altering rule definitions.

Analyze permission denial patterns and generate optimized alwaysAllow and alwaysDeny rules.

Apply Perplexity advanced debugging techniques for hard-to-diagnose issues.

Choose and implement Perplexity validated architecture blueprints for different scales.