Skip to content
Cloud Security DeskSearch
Menu

Evidence search

Search

Search titles, summaries, topics, providers, authors, and the full open-access corpus.

Results for “Ai Systems”

38 publications
Technical guideSource-based analysis

Run AI coding agents in GitHub Actions without exposing secrets

Treat the agent job as an untrusted-input processor. Follow the outside text from the trigger that admits it to the credentials it can reach, then split reading from writing so a successful injection reaches nothing worth stealing.

AI systems · GitHub / Anthropic / Google / Microsoft · By Cloud Security Desk
Technical guideSource-based analysis

Treat a cloud model retirement as a security change

Bedrock and Agent Platform fail closed on a model's retirement date, while Foundry can swap a different model in behind the same deployment name. Read the three calendars, compare the replacement's controls and decide per deployment.

AI systems · Amazon Web Services / Microsoft Azure / Google Cloud · By Cloud Security Desk
Technical guideSource-based analysis

Admit MCP servers before agents can call their tools

An MCP server's tool descriptions can change after approval with no new release. Record provenance and execution context, hash the definitions per authorization context, enforce the pin at a gateway or allowlist, and watch for drift.

AI systems · MCP / AWS / Anthropic / GitHub / Microsoft Azure / Google Cloud / OWASP · By Cloud Security Desk
Technical guideSource-based analysis

Lock down self-hosted model servers before exposing them

Built-in credentials in vLLM, SGLang and Triton cover less than their names suggest, Ollama's local API has none, and vLLM and SGLang leave their internal planes unauthenticated. Here is what stays open and what must sit in front.

AI systems · vLLM / SGLang / Ollama / NVIDIA Triton Inference Server / Kubernetes / nginx · By Cloud Security Desk
Technical guideSource-based analysis

Validate the judge before trusting automated AI evaluations

Managed agent evaluators score your traces with a second model. Measure that judge against your own reviewers with chance-corrected agreement, probe its biases, and pin the judge model before its pass rate gates a release.

AI systems · Amazon Web Services / Microsoft Azure / Google Cloud · By Cloud Security Desk
Technical guideSource-based analysis

Keep semantic response caches inside authorization scope

A semantic cache returns whatever its nearest stored prompt earned. Put tenant, user or entitlement scope, template and model into an exact-match partition, close the write path, and treat thresholds as a correctness setting.

AI systems · Microsoft Azure / Google Cloud / Redis / GPTCache / Amazon Web Services · By Cloud Security Desk
Technical guideSource-based analysis

Map the OWASP Top 10 for Agentic Applications to cloud controls

Each OWASP agentic risk mapped to the controls AWS, Microsoft and Google document for their agent platforms, with a plain account of which risks no infrastructure setting can close.

AI systems · OWASP GenAI Security Project / Amazon Web Services / Microsoft Azure / Google Cloud · By Cloud Security Desk
Technical guideSource-based analysis

Design AI agents that contain indirect prompt injection

Filters lower the odds that an agent obeys injected text. Architecture decides what an obeying agent can reach. Compare six published patterns and CaMeL by what each removes, what it costs and what it still misses.

AI systems · Google DeepMind / AgentDojo / NIST / OWASP / Microsoft · By Cloud Security Desk
Technical guideSource-based analysis

Know where cloud AI services process your prompts

Bedrock inference profiles, Foundry deployment types and Agent Platform endpoints each decide where a prompt is processed, separately from where data rests. Compare what each provider commits to and how to enforce it.

AI systems · Amazon Web Services / Microsoft Azure / Google Cloud · By Cloud Security Desk
Technical guideSource-based analysis

Compare managed prompt attack filters in Bedrock, Azure and Vertex AI

Bedrock Guardrails, Azure Prompt Shields and Google Cloud Model Armor all score text for injected instructions. They differ in which content reaches the classifier, how you mark it, and what each one skips.

AI systems · Amazon Web Services / Microsoft Azure / Google Cloud · By Cloud Security Desk
Technical guideSource-based analysis

Run code written by AI agents inside a disposable sandbox

Treat agent-generated code as untrusted input. Pick a microVM or user-space kernel boundary, keep egress and credentials off by default, and destroy the session when the user or conversation ends.

AI systems · Amazon Web Services / Microsoft Azure / Google Cloud / Firecracker / gVisor / OWASP · By Cloud Security Desk
Technical guideSource-based analysis

Track EU AI Act deadlines after the Digital Omnibus delay

The Digital Omnibus moved high-risk AI duties to December 2027 and August 2028, but prohibitions, AI literacy and Article 50 transparency already apply. See which dates moved and what cloud teams should build now.

AI systems · European Union / European Commission · By Cloud Security Desk
Technical guideSource-based analysis

Count tokens before sending a prompt to Amazon Bedrock

Count a Bedrock prompt for the chosen model, check endpoint support, distinguish context and output limits, and verify usage without logging prompts.

AI systems · AWS · By Cloud Security Desk
Technical guideSource-based analysis

Remove a document from an Amazon Bedrock knowledge base

Retire an S3 document from a Bedrock knowledge base through source changes, sync results, retrieval checks, and review of older application copies.

AI systems · AWS · By Cloud Security Desk
Technical guideSource-based analysis

Call Vertex AI from Cloud Run without a service account key

Use a Cloud Run service account and ADC to call Vertex AI, separate deployment and runtime permissions, and remove an obsolete prototype key.

AI systems · Google Cloud · By Cloud Security Desk
Technical guideSource-based analysis

Remove unnecessary personal data before sending Vertex AI prompts

Reduce personal data in Vertex AI prompts with field selection, Sensitive Data Protection, deliberate transformations, and safe failure handling.

AI systems · Google Cloud · By Cloud Security Desk
Technical guideSource-based analysis

Handle Azure OpenAI rate limits without retry storms

Separate deployment quota, short request bursts and bounded client retry behavior.

AI systems · Azure · By Cloud Security Desk
Technical guideSource-based analysis

Connect to Azure OpenAI without an API key

Prove Entra-based inference with a scoped runtime identity before disabling local authentication.

AI systems · Azure · By Cloud Security Desk
Technical guideSource-based analysis

Bind confidential GPU inference to a verified key release

Require composite evidence, owner policy and verified recipient binding before confidential inference receives protected key material.

AI systems · NVIDIA / Azure · By Cloud Security Desk
Technical guideSource-based analysis

Choose who can share an inference prefix cache

Choose the principals allowed to share prefix state, then carry that decision through request routing, offload, transfer and restore.

AI systems · vLLM / NVIDIA · By Cloud Security Desk
Research noteSource-based analysis

Embeddings still need a sensitive data boundary

Treat vector access as a derived-data release decision, with separate permissions for retrieval, debugging and bulk export.

AI systems · By Cloud Security Desk
Technical guideSource-based analysis

Give persistent agent memory an admission boundary

Separate conversational candidates from admitted memory, preserve their permitted audience, and make derived summaries repairable.

AI systems · LangChain · By Cloud Security Desk
Technical guideSource-based analysis

Isolate document parsing before RAG ingestion

Give document parsing a bounded worker, then admit its extracted content separately before embedding or indexing.

AI systems · Apache Tika / Kubernetes / gVisor · By Cloud Security Desk
Technical guideSource-based analysis

Decide what happens when an AI guardrail fails

Distinguish denial, incomplete checks and late results, then decide what may cross each protected release point.

AI systems · Algolia / TrueFoundry / Conductor · By Cloud Security Desk