Basic Concept: Generative AI produces natural language content based on input data. In a security operations context, triage involves rapidly understanding and prioritizing security events. Generative AI ' s strength lies in synthesizing information and producing readable summaries from complex data. CompTIA SecAI+ Study Guide covers generative AI applications in security operations.

Why C is Correct: Summarizing security findings by category is a natural application of generative AI in triage. The AI can process large volumes of alerts and security events, group them by type or severity, and generate concise natural language summaries that enable analysts to quickly understand the current threat landscape without reading individual alerts. This directly reduces triage time and cognitive load.

Why A is Wrong: Predicting the next attack target requires predictive analytics and threat intelligence correlation. While AI can assist with this, it is a forecasting task better suited to analytical ML models rather than generative AI, and it is a strategic intelligence function rather than a triage task.

Why B is Wrong: Statistical analysis for malicious code assessment uses mathematical and ML techniques to analyze code characteristics. This is a traditional ML classification task, not a generative AI application, and is performed during malware analysis rather than alert triage.

Why D is Wrong: Tagging malware using ML algorithms is a classification task that uses supervised ML models trained on malware features. It is a detection and classification function, not a generative AI triage application.

Option B is correct because a human resources AI application processes highly sensitive employee and applicant information and may influence consequential employment decisions. Privacy and security therefore determine whether the system can be deployed responsibly. The design must address data minimization, lawful collection, access control, encryption, retention, auditability, secure model integration, and protection against unauthorized disclosure. It should also evaluate whether training data or outputs expose protected or confidential information and whether human review is required before decisions affect candidates or employees. Option A concerns friendliness and presentation, not the protection of people or organizational data. Option C may improve usability, but visual design cannot compensate for insecure handling of resumes, performance records, or identity data. Option D can make outputs easier to consume, yet brevity and summarization do not control privacy risk or system compromise. The NIST AI Risk Management Framework identifies privacy enhancement, security, resilience, accountability, and transparency as characteristics of trustworthy AI, making privacy and security the controlling considerations in this scenario.

================

The data scientist is the most appropriate role because correcting biased source data requires examining the datasets used to develop, train, validate, or refine the model and then modifying the data preparation or model-development process. Data scientists work directly with training data, feature selection, statistical distributions, model development, and evaluation, which places them in the strongest position to identify biased inputs and retrain or adjust the model using more representative information. CompTIA SecAI+ includes the data scientist as a formal AI governance role and separately identifies fairness, introduction of bias, accuracy, and model performance as key responsible-AI risks. A platform engineer primarily manages the infrastructure supporting AI workloads. A cybersecurity analyst focuses on security threats, monitoring, and defensive controls rather than correcting discriminatory training data. An AI architect designs the broader architecture and integration of AI solutions but normally does not perform the detailed dataset preparation and model-training work required here. Because the problem originates in biased data sources, the data scientist is the role closest to the underlying cause.

================

Basic Concept: Human-in-the-loop is a design pattern where AI systems generate recommendations or decisions but require human review and approval before those recommendations are acted upon. This approach maintains human oversight and accountability in AI-assisted workflows. CompTIA SecAI+ Study Guide covers human-in-the-loop as a key responsible AI principle and operational pattern.

Why C is Correct: The scenario precisely describes the human-in-the-loop pattern: the AI system identifies potential issues and provides recommendations, but an administrator must review those recommendations before any action is taken. This deliberate inclusion of human judgment in the AI ' s decision or recommendation workflow ensures human oversight is maintained, which is the defining characteristic of the human-in-the-loop process.

Why A is Wrong: Data validation verifies that data meets expected quality standards and formats before being used in AI processing. It is a data quality control activity, not a workflow pattern describing human review of AI recommendations.

Why B is Wrong: Data preparation involves transforming raw data into a format suitable for AI model training or inference. It encompasses cleaning, normalizing, and formatting data, not the process of human review of AI-generated recommendations during system updates.

Why D is Wrong: Model evaluation assesses a model ' s performance against metrics such as accuracy, precision, and recall on test datasets. It is a technical assessment of model quality, not a workflow process where humans review AI-generated recommendations before acting on them.

Basic Concept: Generative AI chatbots interact with users in natural language and may access organizational knowledge bases, databases, or prior conversations. The conversational nature of these systems creates unique risks around sensitive information disclosure. CompTIA SecAI+ Study Guide ranks data leakage as the primary security concern for generative AI chatbots.

Why B is Correct: Data leakage occurs when a generative AI chatbot inadvertently reveals sensitive information including PII, confidential business data, intellectual property, training data, or system configurations in its responses. This can happen through prompt injection attacks, insufficient output filtering, or the model memorizing and reproducing sensitive training data. The impact is immediate, potentially irreversible, and can result in regulatory violations, competitive disadvantage, and reputational damage.

Why A is Wrong: Overly permissive access is a contributing factor that can exacerbate data leakage but is an access control design issue rather than the most directly impactful runtime risk of operating a generative AI chatbot.

Why C is Wrong: Weak encryption is a data protection concern for data in transit or at rest. While important, it is a configuration issue separate from the generative AI chatbot ' s core operational risks and is not specific to chatbot technology.

Why D is Wrong: Model validation ensures a model performs as expected before deployment. While important for quality assurance, it is a development lifecycle activity rather than an ongoing operational security risk associated with running a chatbot.

Basic Concept: AI systems that access file systems or databases use service accounts to authenticate. Applying the principle of least privilege to these service accounts limits the damage that can result from prompt injection or other attacks that cause the AI to perform unauthorized file access. CompTIA SecAI+ Study Guide covers least privilege as a core AI security control.

Why D is Correct: Reducing the privilege scope of the service account implements the least privilege principle, ensuring the AI system can only access files it legitimately needs for its intended function. If an attacker uses prompt injection to abuse the file search capability, the service account ' s limited permissions prevent access to sensitive files outside the defined scope, containing the blast radius of any exploitation.

Why A is Wrong: Custom detection rules identify anomalous behavior after it occurs. They are detective controls, not preventive controls. They do not stop an attacker from successfully abusing the system; they only alert after abuse has occurred.

Why B is Wrong: VPC segmentation isolates the workload at the network level, limiting lateral movement. However, it does not restrict what files the AI ' s service account can access within its own environment, so file abuse attacks within the segment are still possible.

Why C is Wrong: LLM guardrails filter prompt inputs and outputs for policy violations. While useful, they can potentially be bypassed through sophisticated prompt injection. Reducing service account privileges provides a defense-in-depth layer that limits damage even if guardrails are bypassed.

Basic Concept: Agentic AI systems that execute shell commands based on model-generated output are vulnerable to prompt injection attacks where malicious actors craft inputs that cause the agent to run unauthorized commands. Input validation using allowlists is a critical defense mechanism. CompTIA SecAI+ Study Guide covers agentic AI security controls.

Why A is Correct: Adding logic that validates shell commands against an approved allowlist before execution is the most direct and effective defense. This ensures only pre-approved, safe commands can be executed regardless of what the agentic system ' s model generates, preventing malicious command injection from reaching the operating system. This principle of allowlist-based input validation is a foundational secure agentic AI control.

Why B is Wrong: Deprecating and retraining the model is a lengthy process that addresses root cause training issues but does not provide immediate protection against ongoing injection attacks in the current deployed system.

Why C is Wrong: Modifying the application to ignore a specific tag merely removes one attack surface while leaving the system vulnerable to other injection vectors. It is not a comprehensive defense.

Why D is Wrong: Using only approved libraries controls which code libraries the agentic system can call, but does not validate or restrict the shell commands generated by the model at runtime based on arbitrary user input.

Basic Concept: Suspicious queries in AI system logs indicate that potentially malicious or policy-violating prompts are reaching the AI model. Proactively intercepting and filtering suspicious prompts before they are processed requires a prompt-level security control. CompTIA SecAI+ Study Guide identifies prompt firewalls as the appropriate control for blocking suspicious AI queries.

Why A is Correct: A prompt firewall analyzes incoming queries using a combination of pattern matching, semantic analysis, and policy rules to identify and block suspicious prompts before they reach the AI model. It can detect prompt injection attempts, jailbreaking patterns, sensitive data extraction queries, and other suspicious prompt characteristics. By intercepting malicious prompts at the perimeter, it prevents them from influencing model behavior or extracting sensitive information.

Why B is Wrong: Data size controls limit the volume or size of data in requests. While controlling input size can prevent some attacks, it does not analyze the content or semantics of queries to detect suspicious patterns. A small suspicious prompt can be just as harmful as a large one.

Why C is Wrong: Rate limiting controls the frequency of requests from a source. While it can slow down automated attack campaigns, it does not inspect query content for suspicious patterns and allows suspicious queries through as long as they are submitted below the rate threshold.

Why D is Wrong: Agentic AI is an AI architecture for autonomous multi-step task execution. It is a type of AI system, not a security control for filtering suspicious queries from an existing AI system ' s logs.

The described problem is hallucination: the LLM is generating plausible-looking information that is not grounded in real-world facts. Retrieval-augmented generation is the best option because RAG supplements the model ' s prompt with information retrieved from an authoritative external knowledge source before the response is generated. This allows incident- management responses to be grounded in actual tickets, security documentation, threat intelligence, asset information, or other trusted records instead of relying exclusively on the model ' s internal parameters. CompTIA SecAI+ explicitly includes RAG, vector storage, and embeddings within its AI data concepts and also identifies hallucinations as an issue that organizations must monitor and audit. Watermarking helps identify AI-generated content but does not improve factual grounding. Output filtering can block prohibited or unsafe output patterns, but it cannot reliably supply missing factual information. Data rebalancing addresses uneven distributions in training datasets and is unrelated to grounding an LLM ' s incident-management responses. RAG therefore most directly reduces unsupported or fabricated information by giving the model relevant factual context at inference time.

================

Option B is correct because patching critical vulnerabilities directly removes or reduces known exploitable weaknesses while allowing the essential AI service to remain available. The organization should prioritize patches according to exploitability and impact, test them in a representative environment, use redundancy or rolling deployment where possible, and verify that remediation succeeded. Option A would weaken confidentiality and create an additional security exposure; encryption is not the obstacle to secure continuous operation. Option C is valuable as a detective control because log analysis can reveal abnormal activity, but it does not remediate a known critical vulnerability. Option D redeploys the production model, which may restore model files or configuration, but it does not necessarily update the vulnerable operating system, library, container, API, or orchestration component. For a system that cannot be shut down, the correct strategy is controlled patch management supported by high availability, maintenance coordination, monitoring, and rollback capability. NIST describes enterprise patch management as preventive maintenance that reduces the likelihood of compromise, breaches, and operational disruption.

================