Practical defence library
Short, printable guidance for AI-enabled attacks, secure AI, agents, MCP, RAG, data handling, supply-chain assurance, incident response and defensive AI operations.
Guide library
Search by situation or filter by control area. Every guide opens as a clean reading page with a quick-action panel, checklist, references and print support.
A calm, trusted-channel response to cloned voices, synthetic video and urgent impersonation requests.
A practical decision path for prompts, uploads, chat history, AI workspaces and connected information sources.
Reduce agentic AI risk with bounded actions, minimum access, approval points, audit trails and safe failure.
Protect AI applications that read webpages, files, email, retrieved records or user-controlled instructions.
A repeatable response when a senior leader appears to request payment, access, secrecy or urgent disclosure.
Find unsanctioned AI use, understand why it exists and replace risky workarounds with approved pathways.
Questions that turn an AI demonstration into a reviewable security, privacy, resilience and accountability decision.
Calm containment steps for a suspicious login, stolen session, malicious mailbox rule or account-recovery scam.
A deployment checklist for agent identities, tools, memory, approvals, logging, limits and safe shutdown.
A practical MCP review covering authorization, token audience, servers, tools, consent, logs and revocation.
Protect retrieval-augmented generation from poisoned documents, indirect prompt injection and excessive data access.
Keep credentials, private code and sensitive configuration out of unapproved AI workflows.
Contain an unsafe or compromised AI workflow while preserving prompts, tools, identities, data and downstream evidence.
Track model, dataset, provider, library and connector provenance so material changes do not silently change risk.
A controlled pattern for AI-assisted vulnerability, threat, phishing, detection and incident work.
Try a broader phrase or choose “All”.
EVIDENCE BEFORE ACTION
Choose the guide that matches a likely scenario and identify trusted contacts.
Replace general terms with real approval paths, providers and evidence locations.
Practise pausing, verifying, escalating and recording under realistic pressure.
Need an organisation-specific version?
Align verification, escalation, evidence and decision ownership with your real systems and teams.
