Prompt Injection Firebreak
Design hard prompt boundaries, tool gating, and context sanitization so indirect prompt injection has fewer places to land.
Collection
Threat reduction, policy hardening, release hygiene, and trustworthy AI operations.
39 skills in this lane
Design hard prompt boundaries, tool gating, and context sanitization so indirect prompt injection has fewer places to land.
Embed privacy-first product patterns with data minimization, retention controls, and defensible deletion workflows.
Review an MCP server for prompt-exfiltration, shell abuse, overbroad tool scope, and unsafe logging.
Audit a repo for secrets, personal paths, client-specific references, and OSS-readiness gaps before publishing.
Build a practical threat model for agent workflows, MCP tools, provider routing, and persisted run data.
Coordinates comprehensive red team exercises targeting AI systems with automated attack generation, vulnerability discovery, and remediation tracking
Tests API security with OWASP API Top 10 coverage, authentication validation, and automated security test cases that find vulnerabilities before attackers
Protect critical audit trails against tampering with append-only integrity and verification strategies.
Implements least-privilege IAM policies with automated permission analysis, access reviews, and policy optimization that eliminates over-permissioning
Continuously monitors cloud security posture with automated compliance checks, drift detection, and remediation that maintains security baselines
Secures containerized workloads with image scanning, runtime protection, network policies, and pod security that prevents container escapes
Design nonce- and policy-based browser defenses that meaningfully shrink XSS blast radius.
Architects continuous validation systems that verify trust dynamically with behavioral analytics, anomaly detection, and automated response that maintains zero trust
Tighten cross-origin boundaries without silently breaking legitimate credentialed traffic.
Ensures data residency compliance with geographic controls, encryption key management, and cross-border transfer mechanisms that meet regulatory requirements
Audit dependencies for typosquatting, licensing risk, and supply-chain fragility before they hit production.
Implements device trust verification with health attestation, compliance checking, and conditional access that ensures only trusted devices access resources
Implements HIPAA technical safeguards with encryption, access controls, audit logging, and breach notification procedures that protect PHI and ensure compliance
Guides organizations through ISO 27001 certification with gap analysis, control implementation, documentation, and audit preparation that achieves certification on first attempt
Designs comprehensive LLM gateway infrastructure with unified security controls, traffic management, and observability that secures all AI interactions
Implements real-time output filtering that prevents data leakage, harmful content, and policy violations before responses reach users
Detects and prevents model extraction attacks by monitoring query patterns, rate limiting, and implementing response perturbations
Designs micro-segmentation architectures with workload isolation, east-west traffic controls, and policy-based segmentation that limits lateral movement
Implements NIST CSF with risk assessment, current/target profile development, and gap remediation that improves cybersecurity posture measurably
Systematically surface high-probability application security weaknesses across common OWASP failure modes.
Validates payment card data security with network segmentation, encryption, vulnerability management, and audit trails that achieve PCI-DSS compliance
Builds multi-layered prompt injection defenses with input validation, context isolation, and adversarial testing that blocks jailbreak attempts
Orchestrates Static Application Security Testing with multi-tool integration, result correlation, and developer-friendly remediation that catches vulnerabilities early
Generates comprehensive Software Bill of Materials with dependency tracking, vulnerability mapping, and attestation that enables supply chain transparency
Implements enterprise secrets management with HashiCorp Vault or cloud-native solutions, including dynamic credentials, rotation, and audit logging
Wire secret-detection into local and CI workflows so leaks are stopped before they become incidents.
Conducts security-focused code reviews with vulnerability detection, secure coding guidance, and knowledge transfer that improves team security awareness
Secures serverless architectures with function-level permissions, API security, dependency scanning, and runtime protection for Lambda and cloud functions
Translate operating practices into audit-friendly SOC 2 evidence maps with technical verification hooks.
Analyzes open-source dependencies with vulnerability detection, license compliance, and automated remediation that secures the software supply chain
Rank vulnerability work by exploitability and business impact instead of raw advisory volume.
Implements strong identity verification with MFA, device trust, risk-based authentication, and continuous validation that ensures only legitimate access
Plans zero trust network transformations with phased migration, legacy integration, and measurable outcomes that modernize security architecture
Design service-to-service trust boundaries with strong identity, policy, and transport guarantees.