Claude Skills by maruakshay

Review an AI system's robustness against adversarial evasion attacks — covering input perturbation, semantic-preserving transformations that flip classifier decisions, transferability of attacks across model versions, and robustness evaluation methodology.

Review agentic AI systems for long-term memory store poisoning, vector DB manipulation, cross-session instruction injection, and stale memory exploitation that persists attacker influence across agent sessions.

Review a multi-agent or orchestrated AI system for agent-to-agent prompt injection, trust transitivity failures, planner-to-worker privilege spread, unsafe delegation, and cross-agent action escalation.

Review AI agent systems for agent impersonation, capability escalation, missing agent identity primitives, and authorization failures that allow agents to act beyond their granted permissions or impersonate other agents or human users.

Review organizational defenses against AI-assisted spearphishing, voice cloning, synthetic identity fraud, deepfake executive impersonation, and AI-accelerated reconnaissance that dramatically lowers the barrier to highly targeted social engineering attacks.

Review an AI system's audit logging for completeness, tamper-resistance, and regulatory readiness — covering what events to log for LLM interactions, how to prevent log manipulation, retention requirements, and structured log schemas for AI-specific events.

Review AI-generated content pipelines for deepfake detection gaps, provenance chain failures, C2PA implementation correctness, synthetic media attribution, and trust signal spoofing that undermines content authenticity verification.

Review an AI system for weak model version control, missing rollback plans, unsafe guardrail change workflows, inadequate regulated audit trails, and incident response gaps specific to LLM and agentic failures.

Review an AI system's compliance with GDPR, CCPA, and sector-specific privacy regulations — covering lawful basis for AI processing, PII in training data and prompts, data subject rights in AI contexts, automated decision-making disclosure requirements, and cross-border model API transfers.

Design and operate a continuous AI red team program — covering team structure, scope definition, attack scenario libraries, finding severity classification, responsible disclosure to model vendors, and integration with the AI development lifecycle.

Review an AutoGen multi-agent system for inter-agent message spoofing, trust boundary collapse between orchestrator and sub-agents, uncontrolled code execution, and privilege escalation via crafted agent replies.

Review AI browser agents for DOM injection attacks, credential harvesting via web automation, malicious web content that hijacks agent actions, session cookie theft, and phishing sites engineered to exploit browser-controlling AI agents.

Review Docker and Kubernetes configurations for AI workloads — covering privileged container risks for GPU access, model weight volume security, network policy gaps between inference pods, image provenance for ML base images, and secrets management in pod specs.

Review the core prompt layer of an LLM application for prompt injection, jailbreaks, system prompt exposure, weak guardrails, unsafe output handling, and trust-boundary failures across any language or framework.

Review a CrewAI agent system for role-boundary violations, task delegation abuse, tool permission escalation between crew members, and prompt injection via task descriptions or inter-agent context passing.

Review an AI system for leakage of secrets, PII, tenant data, hidden prompts, embeddings, logs, traces, memory, evaluation sets, and training artifacts across languages, frameworks, and deployment models.

Review upstream dataset integrity controls, HuggingFace repository risks, dataset versioning, dependency pinning, and third-party dataset provenance to prevent malicious data from entering training or RAG pipelines.

Review a DSPy application for unsafe signature design, optimizer dataset leakage, prompt-program boundary failures, weak typed output enforcement, and insecure tool-wrapper behavior.

Review an embedding pipeline for vector database poisoning, embedding inversion attacks, cross-tenant retrieval leakage, adversarial query perturbations, and semantic similarity abuse that allows attacker-controlled content to dominate retrieval results.

Review a federated learning system for poisoned gradient attacks, model update tampering by malicious participants, aggregation server compromise, Byzantine fault tolerance gaps, and privacy leakage through gradient inversion.

Review a fine-tuning pipeline for poisoned training data, backdoor triggers, RLHF manipulation, adapter-layer tampering, dataset contamination, and evaluation gaps that mask behavioral drift in fine-tuned or adapted models.

Review GPU infrastructure for shared tenancy risks — VRAM residue between workloads, GPU memory not cleared between jobs, CUDA context isolation failures, side-channel attacks via GPU timing, and credential exposure in GPU compute environments.

Review a Guardrails AI integration for validator bypass via adversarial inputs, schema enforcement gaps that allow malformed LLM output to pass validation, fail-open error handling that silently drops failed guardrails, and RAIL spec injection.

Review a Haystack retrieval pipeline for router scope failures, insecure document-store access, weak grounding, metadata-filter bypass, and leakage through pipeline components or evaluators.

Review AI agent systems for approval step circumvention, human-in-the-loop bypass patterns, deferred confirmation exploitation, and social engineering techniques that cause human reviewers to approve malicious agent actions.

Review an AI system for prompt injection delivered through retrieved documents, web pages, emails, tickets, code repositories, API responses, or tool output rather than directly from the end user.

Review inference APIs for credential stuffing, rate limit bypass, quota exhaustion, account takeover, and systematic abuse patterns that exploit the high cost-per-request nature of LLM inference.

Catalog of jailbreak technique families — persona adoption, fictional framing, token manipulation, gradual escalation, and authority impersonation — with detection patterns, defense mappings, and severity ratings for each class.

Review a LangChain retrieval augmented generation stack for document poisoning, retriever scope failures, insecure chain composition, weak citation grounding, metadata filter bypass, and leakage from callbacks, memory, or intermediate steps.

Review a LiteLLM proxy deployment for API key leakage through the proxy layer, model routing abuse, budget enforcement bypass, insecure master key configuration, and database credential exposure in the proxy config file.

Review a llamafile local inference deployment for unsafe model artifact handling, exposed HTTP server attack surface, local filesystem and process access risks, and absence of access controls on a single-binary inference endpoint.

Review a LlamaIndex retrieval augmented generation stack for ingestion poisoning, node metadata loss, retriever scope failures, insecure query-engine composition, weak source attribution, and leakage through storage, memory, or observability layers.

Review AI systems for LLM-specific denial-of-service vulnerabilities including token flooding, recursive prompt expansion, sponge attacks, computational complexity exploitation, and resource exhaustion patterns that degrade availability for all users.

Review an AI system for persistent memory poisoning, unsafe episodic or long-term memory writes, retrieval scope failures, stale or undeletable memory state, and cross-session influence over future model behavior.

Review an MLOps CI/CD pipeline for unsigned model artifacts, insecure experiment tracking, training job privilege escalation, poisoned pipeline triggers, and absence of artifact integrity checks between pipeline stages.

Review KV cache, prompt cache, and semantic cache implementations for cross-request context leakage, cache poisoning, sidecar timing attacks, and tenant isolation failures in shared inference infrastructure.

Review an AI system for model inversion attacks that reconstruct training data from model outputs, and membership inference attacks that determine whether specific individuals' data was used in training — covering API query patterns, confidence score leakage, and differential privacy mitigations.

Review a model serving layer for API gateway misconfiguration, rate limit bypass, inference DoS through token exhaustion, response streaming abuse, unauthenticated endpoints, and SSRF via model-generated URLs.

Review a model acquisition and deployment pipeline for poisoned base models, unsafe fine-tunes, trojaned adapters, unverifiable provenance, weak artifact integrity, and overtrust in third-party model documentation.

Review AI systems for model theft, unauthorized redistribution, and IP leakage using watermarking, fingerprinting, and behavioral probing techniques to detect stolen or leaked model weights.

Review multi-tenant AI deployments for cross-tenant context leakage, LoRA adapter contamination, shared inference worker risks, system prompt bleed, and tenant isolation failures in model serving infrastructure.

Review multi-agent AI systems for Byzantine agent attacks, consensus manipulation, coordinated deception by colluding agents, and orchestration failures that allow a minority of compromised agents to subvert system-wide decisions or outputs.

Review a multimodal AI system for adversarial images, OCR prompt injection, hidden text, typographic attacks, unsafe visual grounding, and vision-to-action trust-boundary failures.

Review a NeMo Guardrails deployment for Colang flow bypass via adversarial inputs, rail definition injection, action server exposure, dialog manager manipulation, and trust assumption gaps between the guardrail layer and the underlying LLM.

Review an Ollama deployment for unauthenticated API exposure, model pull from untrusted registries, CORS misconfiguration enabling cross-origin inference abuse, and absence of resource controls on a local inference server.

Review a legacy OpenAI Assistants API integration for unsafe thread and run reuse, attachment scope failures, hosted tool exposure, and migration risk to newer interfaces.

Review an OpenAI Responses API integration for unsafe hosted-tool exposure, file-search scope failures, function-calling validation gaps, and conversation-state or tool-loop escalation.

Review AI systems for output fingerprinting risks, stylometric attribution vulnerabilities, authorship identification through AI outputs, and detection of model-specific generation signatures that expose model identity or user attribution.

Apply offensive red-teaming methodology to evaluate prompt injection defenses — covering attack categorization, systematic probe generation, success metrics, responsible disclosure, and continuous evaluation pipeline design.

Review a retrieval augmented generation system for ingestion poisoning, retrieval boundary failures, insecure chunking and metadata handling, document trust confusion, and cross-tenant or stale-context exposure across any language or framework.