Database

Design the tools that an LLM agent uses. Covers naming, parameter

Build the eval suite that tells you whether changes to your agent

Use LangGraph (or equivalent state-machine frameworks) to express

Build the episodic memory layer that stores specific past events and

Build the agent's accumulated model of the user — preferences, expertise,

Design the memory architecture for a stateful agent — what's in

Implement an agent memory system using a vector database with retrieval-

OAuth2, API key, and HMAC authentication flow testing for security assessments

Rate limiting bypass testing, throttle evasion, and abuse prevention assessment

API schema validation testing, fuzzing, and type confusion attacks

Third-party API integration risk assessment and supply chain security testing

JWT/OAuth token analysis, validation, and expiry testing for API security assessments

Webhook trust boundary testing, signature verification, and callback security

AWS security posture review including S3 exposure, IAM policies, and CloudTrail for authorized assessments

Azure security assessment including Entra ID, NSGs, and Key Vault for authorized security assessments

CloudTrail, Azure Monitor, and GCP logging coverage gap assessment for authorized security assessments

VPC rules, security groups, and cloud network segmentation assessment for authorized security assessments

Public bucket and blob detection, storage ACL review for authorized security assessments

GCP security review including service accounts, storage, and VPC for authorized security assessments

Alert quality review, noise reduction, and detection tuning methodology

Detection rule writing, SIGMA/YARA rule development, and behavioral detection

Forensic log retention assessment, evidence preservation, and attack traceability

IR handoff quality assessment, playbook review, and communication evaluation

SIEM coverage assessment, log source gaps, and detection blind spot analysis

Proactive threat hunting methodology with hypothesis-driven search techniques

Container image hygiene, Kubernetes RBAC, and pod security assessment

EDR and antivirus coverage gap analysis and blind spot detection

Local privilege escalation testing including SUID, sudo abuse, and service misconfiguration

OS hardening assessment for Linux and Windows systems against CIS benchmarks

Cron job and scheduled task abuse risk assessment and service hijacking

Software inventory anomaly detection, shadow IT discovery, and EOL software identification

Exploitability confirmation and false positive reduction methodology

Impact verification, blast radius estimation, and business consequence assessment

Controlled proof-of-concept execution and safe vulnerability validation

Post-exploitation risk mapping including pivot paths and persistence mechanisms

CVE matching, version risk analysis, and misconfiguration detection methodology