Search

24 results for “security” (members search the full text)

• PromptBuilderAny assistantDefensive Security Review ChecklistDeclaring scope and authorization up front keeps the output defensive and focused.
• PromptBuilderPerplexitySecurity Advisory LookupPointing the search at official advisories first reduces reliance on rumor.
• GuideBuilderAny assistantReviewing AI-Written Code - Tests, Security and Common TrapsHow to review code from an assistant: what to read first, what to test, the security mistakes that appear again and again, and when to throw it away.
• AgentBuilderAny assistantSecurity Alert ExplainerExplains a security alert in plain English, rates how worried to be, and lists defensive checks and who to escalate to. No offensive guidance.
• GuideProAny assistantPrompt Injection Explained: The Attack Every AI Builder Should KnowWhat prompt injection is, how it hits chatbots and agents through documents and web pages, and layered defenses that reduce the risk.
• PromptBuilderAny assistantPre-Merge Code ReviewA defined checklist and table make the review consistent and scannable.
• AgentBuilderAny assistantCareful Code ReviewerReviews a code change for bugs, security issues and clarity, reporting only findings it can justify, with severity and a suggested fix.
• AgentBuilderAny assistantConfig Reviewer for Dockerfile, CI Pipeline and NginxReviews a Dockerfile, CI pipeline or nginx configuration for security and reliability problems and reports ranked findings with safe fixes.
• AgentProAny assistantMaster Code VerifierVerifies a function or script in several passes, from spec to edge cases to security, and only gives a verdict backed by evidence and runnable test cases.
• GuideProAny assistantGiving Agents Tools Safely: Permissions, Limits and ApprovalsHow to design agent tools with least privilege, spending caps, confirmation steps and audit logs so a mistake stays small and reversible.
• GuideBuilderAny assistantMCP in Practice - Connecting AI to Tools SafelyWhat the Model Context Protocol does, how servers and clients fit together, how to try one, and how to vet a server before you trust it.
• GuideProAny assistantDefending Against Prompt Injection in Your AI AppsThere is no single fix for prompt injection, but layered defenses work. Learn the practical controls: privilege limits, approvals, isolation and testing.
• PromptProAny assistantAgent Red-Team ChecklistDescribing the agent's tools and data lets the checklist target real risks instead of generic ones.
• AgentStarterLlamaPhishing Email AnalyzerHelps staff judge a suspicious email by walking through sender, links, urgency and attachments, then says what to do. Defensive use only.
• GuideStarterAny assistantKeeping Your Private Data Safe When Using AIWhat not to paste into an AI chat, how to check privacy settings, and simple habits that protect you and your employer.
• GuideStarterAny assistantWriting an AI Use Policy for a Small CompanyA practical template for a one-page AI use policy: approved tools, data rules, review requirements and what to do when something goes wrong.
• PromptBuilderChatGPTHelpdesk Assistant Custom GPT InstructionsSpelling out what the GPT must not do and when it escalates is what makes a support bot safe to use.
• PromptBuilderLlamaLog Line ClassifierA closed label set and a fixed output format suit local models and make results easy to scan or paste into a spreadsheet.
• Q&AStarterAny assistantHow can I use AI at work without leaking company data?Use only company-approved AI tools and accounts for work material, and keep confidential data out of anything unapproved.
• Q&AStarterAny assistantHow do I write a good system prompt?A good system prompt states the assistant's role, what it should and should not do, its tone, the output format, and what to do when it is unsure.
• Q&AStarterAny assistantWhat is MCP, the Model Context Protocol, for AI tools?MCP, short for Model Context Protocol, is an open standard for connecting AI assistants to tools and data sources through a common interface.
• Q&AStarterAny assistantWhat should I do if my AI API key leaked on GitHub?Revoke the leaked key immediately in the provider's console, then create a new one.
• AgentProAny assistantCustomer Support Triage BotClassifies incoming support messages by topic and urgency, drafts a suggested reply, and escalates sensitive cases to a human.
• AgentBuilderDeepSeekDeepSeek Reasoning Code Review BotA small Python command-line bot that sends one source file to the DeepSeek chat API in reasoning mode and prints a prioritized code review.