Topic: ai-agents
18,135 skills in this topic.
-
performing-bandwidth-throttling-attack-simulation
Simulates bandwidth throttling and network degradation attacks using tc, iperf3, and Scapy in authorized environments to test quality-of-service controls, application resilience, and network monitoring detection of traffic manipulation attacks.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
detecting-attacks-on-scada-systems
This skill covers detecting cyber attacks targeting Supervisory Control and Data Acquisition (SCADA) systems including man-in-the-middle attacks on industrial protocols, unauthorized command injection into PLCs, HMI compromise, historian data manipulation, and denial-of-service against control system communications. It leverages OT-specific intrusion detection systems, industrial protocol anomaly detection, and process data analytics to identify attacks that traditional IT security tools miss.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
implementing-threat-modeling-with-mitre-attack
Implements threat modeling using the MITRE ATT&CK framework to map adversary TTPs against organizational assets, assess detection coverage gaps, and prioritize defensive investments. Use when SOC teams need to align detection engineering with threat landscape, conduct threat assessments for new environments, or justify security tool procurement.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
exploiting-race-condition-vulnerabilities
Detect and exploit race condition vulnerabilities in web applications using Turbo Intruder's single-packet attack technique to bypass rate limits, duplicate transactions, and exploit time-of-check-to-time-of-use flaws.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
hunting-for-lolbins-execution-in-endpoint-logs
Hunt for adversary abuse of Living Off the Land Binaries (LOLBins) by analyzing endpoint process creation logs for suspicious execution patterns of legitimate Windows system binaries used for malicious purposes.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
triaging-security-incident
Performs initial triage of security incidents to determine severity, scope, and required response actions using the NIST SP 800-61r3 and SANS PICERL frameworks. Classifies incidents by type, assigns priority based on business impact, and routes to appropriate response teams. Activates for requests involving incident triage, security alert classification, severity assessment, incident prioritization, or initial incident analysis.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
performing-threat-modeling-with-owasp-threat-dragon
Use OWASP Threat Dragon to create data flow diagrams, identify threats using STRIDE and LINDDUN methodologies, and generate threat model reports for secure design review.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
configuring-tls-1-3-for-secure-communications
TLS 1.3 (RFC 8446) is the latest version of the Transport Layer Security protocol, providing significant improvements over TLS 1.2 in both security and performance. It reduces handshake latency to 1-R
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
detecting-spearphishing-with-email-gateway
Spearphishing targets specific individuals using personalized, researched content that bypasses generic spam filters. Email security gateways (SEGs) like Microsoft Defender for Office 365, Proofpoint,
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
performing-post-quantum-cryptography-migration
Assesses organizational readiness for post-quantum cryptography migration per NIST FIPS 203/204/205 standards. Performs cryptographic inventory scanning to identify quantum-vulnerable algorithms (RSA, ECDH, ECDSA), evaluates hybrid TLS configurations with X25519MLKEM768, and validates CRYSTALS-Kyber (ML-KEM) and CRYSTALS-Dilithium (ML-DSA) readiness. Implements crypto-agility assessment using oqs-provider for OpenSSL. Use when planning or executing the transition from classical to post-quantum cryptographic algorithms across enterprise infrastructure.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
implementing-azure-ad-privileged-identity-management
Configure Microsoft Entra Privileged Identity Management to enforce just-in-time role activation, approval workflows, and access reviews for Azure AD privileged roles.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
performing-privilege-escalation-on-linux
Linux privilege escalation involves elevating from a low-privilege user account to root access on a compromised system. Red teams exploit misconfigurations, vulnerable services, kernel exploits, and w
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
implementing-supply-chain-security-with-in-toto
Implement software supply chain integrity verification for container builds using the in-toto framework to create cryptographically signed attestations across CI/CD pipeline steps.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
triaging-security-alerts-in-splunk
Triages security alerts in Splunk Enterprise Security by classifying severity, investigating notable events, correlating related telemetry, and making escalation or closure decisions using SPL queries and the Incident Review dashboard. Use when SOC analysts face queued alerts from correlation searches, need to prioritize investigation order, or must document triage decisions for handoff to Tier 2/3 analysts.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
configuring-host-based-intrusion-detection
Configures host-based intrusion detection systems (HIDS) to monitor endpoint file integrity, system calls, and configuration changes for security violations. Use when deploying OSSEC, Wazuh, or AIDE for endpoint monitoring, building file integrity monitoring (FIM) policies, or meeting compliance requirements for change detection. Activates for requests involving HIDS configuration, file integrity monitoring, OSSEC/Wazuh deployment, or host-based detection.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
executing-active-directory-attack-simulation
Executes authorized attack simulations against Active Directory environments to identify misconfigurations, weak credentials, dangerous privilege paths, and exploitable trust relationships that could lead to domain compromise. The tester uses BloodHound for attack path analysis, Mimikatz for credential extraction, and Impacket for protocol-level attacks including Kerberoasting, AS-REP Roasting, and delegation abuse. Activates for requests involving Active Directory pentest, AD attack simulation, domain compromise testing, or Kerberos attack assessment.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
deploying-ransomware-canary-files
Deploys and monitors ransomware canary files across critical directories using Python's watchdog library for real-time filesystem event detection. Places strategically named decoy files that mimic high-value targets (financial records, credentials, database exports) in locations ransomware typically enumerates first. Monitors for any read, modify, rename, or delete operations on canary files and triggers immediate alerts via email, Slack webhook, or syslog when interaction is detected, providing early warning before full encryption begins.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
performing-authenticated-scan-with-openvas
Configure and execute authenticated vulnerability scans using OpenVAS/Greenbone Vulnerability Management with SSH and SMB credentials for comprehensive host-level assessment.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
implementing-zero-trust-with-beyondcorp
Deploy Google BeyondCorp Enterprise zero trust access controls using Identity-Aware Proxy (IAP), context-aware access policies, device trust validation, and Access Context Manager to enforce identity and posture-based access to GCP resources and internal applications.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
detecting-ai-model-prompt-injection-attacks
Detects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
implementing-end-to-end-encryption-for-messaging
End-to-end encryption (E2EE) ensures that only the communicating parties can read messages, with no intermediary (including the server) able to decrypt them. This skill implements a simplified version
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
implementing-pod-security-admission-controller
Implement Kubernetes Pod Security Admission to enforce baseline and restricted security profiles at namespace level using built-in admission controller.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
implementing-epss-score-for-vulnerability-prioritization
Integrate FIRST's Exploit Prediction Scoring System (EPSS) API to prioritize vulnerability remediation based on real-world exploitation probability within 30 days.
mukul975/Anthropic-Cybersecurity-Skills 4,300
-
implementing-network-policies-for-kubernetes
Kubernetes NetworkPolicies provide pod-level network segmentation by defining ingress and egress rules that control traffic flow between pods, namespaces, and external endpoints. Combined with CNI plu
mukul975/Anthropic-Cybersecurity-Skills 4,300