Results for “high-risk-ai”

Implements AI safety guardrails including input validation, output filtering, robustness testing, human oversight, and monitoring to prevent harmful outputs and ensure system reliability.

AI Safety Specialist IA — Expert en sécurité IA (alignment, guardrails, filtrage de contenu, test de biais, red teaming)

Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness, providing detailed improvement recommendations with frameworks, testing methodologies, and educational content.

Check any AI agent codebase against the OWASP Agentic Security Initiative (ASI) Top 10 risks, scanning for controls and generating a compliance report.

Assess AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, and agent tool abuse, with MITRE ATLAS mapping and guardrail recommendations.

Apply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.

Build production-ready LLM applications, RAG systems, and intelligent agents with architecture design, model selection, and cost controls.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Read-only OWASP LLM Top 10 audit of app-facing AI features: prompt injection, data leak, supply chain, poisoning, unsafe output, excessive agency, system-prompt leak, RAG/embedding risks, misinformation, unbounded consumption. Use when "audit LLM security", "prompt injection", "jailbreak my chatbot", "is my AI safe".

AI/LLM red-team assessment using the OWASP LLM Top 10 (2025) + OWASP AI Testing Guide (AITG v1, Nov 2025) frameworks, plus OWASP MCP Top 10 runtime testing for agentic/MCP targets. Tests prompt injection, jailbreaks, system prompt leakage, sensitive data extraction, excessive agency, improper output handling, model extraction, content bias, evasion, membership inference, MCP token exposure, MCP command injection, and more. Uses four tools in combination: FuzzyAI (single-turn jailbreak fuzzing), PyRIT (multi-turn orchestrated attacks), Garak (probe-based vulnerability scanning), and promptfoo (plugin-based red-team evaluation). Each tool covers different OWASP categories; running them together gives systematic coverage. Includes a conditional MCP reconnaissance phase and a post-access AI infrastructure phase (chained from /post-exploit). Produces: OWASP LLM Top 10 + AITG + MCP coverage matrix, findings per category, architecture diagram of the AI system, PoCs for confirmed exploits. Chains into /gh-export for

Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.

Scan and audit AI agent skills for security risks before installation, producing a PASS/WARN/FAIL verdict with findings and remediation guidance.

Conduct authorized security assessments of LLM applications and AI agents, covering prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.

Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.

AIDefence security layer with prompt injection blocking, input validation, sandboxed execution, output sanitization, and STRIDE threat modeling.

Configures dynamic threshold alerting policies for Google Cloud Vertex AI Agent Platform agents, monitoring latency, error rates, and quality metrics using Terraform and PromQL.

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.

AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks.

Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.

Guides AI agents to apply advanced mathematical and probabilistic techniques (Bloom filters, HyperLogLog, FFT, etc.) for large-scale data problems where classical algorithms are optimal but math offers better asymptotic bounds.

Expert strategy advisor for products built on LLMs or agents — not general product strategy (see `product-strategy` for that). Use this — proactively and without waiting to be asked — whenever choosing where to apply AI in a product, deciding between RAG and fine-tuning, designing how much autonomy an AI feature should have, evaluating whether an AI feature is actually defensible, or deciding whether to add AI to a feature at all. Also triggers for: "should this be an agent or a simple LLM call", "how much autonomy should this feature have", "RAG vs fine-tuning", "is this AI feature defensible", "our AI feature keeps hallucinating and users don't trust it", "should we build this with AI or just ship it deterministic", "AI product wedge", "what happens to this feature when the models get better", "human-in-the-loop design for AI features". Produces a decision-focused brief: the wedge, the architecture choice, the autonomy level, and the defensibility bet — each with an explicit trade-off.

For analysis/task/review agents using a Professional Skill on models, RAG, agents, evaluation, or safety; not for work without AI decision impact.

AI Manipulation Defense System with self-learning prompt injection detection and adaptive mitigation

Reduces AI API costs by 30-75% by classifying task complexity, checking prompt quality, and routing tasks to the most cost-efficient model tier before execution.

Diagnose and mitigate context degradation patterns including lost-in-middle failures, context poisoning, distraction, confusion, and clash in AI agent systems.

Systematically extract hidden system prompts, core directives, and invisible context intentionally concealed within Large Language Model (LLM) applications. This skill utilizes targeted linguistic engineering and boundary manipulation to bypass prompt opacity.