How to build a production-grade agentic harness using typed Pydantic tools, a DAG planner with parallel asyncio execution, tiered memory, Planner/Worker/Critic role separation, multi-dimensional budgeting with graceful degradation, and structured tracing for observability.
https://data4sci.com/blog/building-an-advanced-agentic-harness
#AI
Please open Telegram to view this post
VIEW IN TELEGRAM
❤1👍1🔥1
⚠️ Going depthfirst: Achieving GitLab RCE via Two Ruby Memory. Corruption Vulnerabilities
Researchers chained two memory-safety flaws in Oj, into remote code execution in a Puma worker. The path begins with an attacker-controlled Jupyter notebook and crosses GitLab, ipynbdiff, CRuby, and jemalloc before reaching function-pointer control.
https://depthfirst.com/research/going-depthfirst-achieving-gitlab-rce-via-two-ruby-memory-corruption-vulnerabilities
#RCE
Researchers chained two memory-safety flaws in Oj, into remote code execution in a Puma worker. The path begins with an attacker-controlled Jupyter notebook and crosses GitLab, ipynbdiff, CRuby, and jemalloc before reaching function-pointer control.
https://depthfirst.com/research/going-depthfirst-achieving-gitlab-rce-via-two-ruby-memory-corruption-vulnerabilities
#RCE
❤1👍1🔥1
🔶 Threat hunt AI: How we built an AI security analyst on AWS for under $500/month
Grow Therapy built a Claude-powered threat hunting system on ECS Fargate and Lambda, querying Snowflake and Datadog logs across 15 sources. A five-phase AI pipeline (data gathering, baseline comparison, enrichment, confidence scoring, adversarial validation) reduces false positives. Total cost: under $500/month.
https://engineering.growtherapy.com/post/threat-hunt-ai-how-we-built-an-ai-security-analyst-on-aws-for-under-500-month
#aws
Grow Therapy built a Claude-powered threat hunting system on ECS Fargate and Lambda, querying Snowflake and Datadog logs across 15 sources. A five-phase AI pipeline (data gathering, baseline comparison, enrichment, confidence scoring, adversarial validation) reduces false positives. Total cost: under $500/month.
https://engineering.growtherapy.com/post/threat-hunt-ai-how-we-built-an-ai-security-analyst-on-aws-for-under-500-month
#aws
❤2👍1🔥1
Datadog tested Claude Sonnet 5, Composer 2.5, and GPT 5.5 in plan vs. default mode for secure code generation. No meaningful correlation between plan mode and improved security was found; explicit prompt-level security constraints had greater impact than mode selection.
https://securitylabs.datadoghq.com/articles/putting-models-to-the-secure-coding-test-plan-vs-default-mode
#AI
Please open Telegram to view this post
VIEW IN TELEGRAM
👍3❤1🔥1
CloudSEK's research on the LiteLLM supply chain attack, the largest AI supply chain breach of 2026, names the organizations potentially exposed: 2,500+ companies and 434,000 CI/CD pipelines worldwide.
https://www.cloudsek.com/blog/ai-supply-chain-breach-2500-companies-434000-cicd-pipelines
#AI
Please open Telegram to view this post
VIEW IN TELEGRAM
❤1👍1🔥1
🔶 Implement custom authentication for tools integration using request Lambda interceptor in AgentCore Gateway
AgentCore Gateway supports OAuth 2.0, IAM, and API keys natively, but a request Lambda interceptor enables legacy Basic Auth integration. The interceptor validates the inbound JWT, retrieves system credentials from Secrets Manager, and constructs the Basic Auth header before forwarding to the downstream tool.
https://aws.amazon.com/ru/blogs/security/implement-custom-authentication-for-tools-integration-using-request-lambda-interceptor-in-agentcore-gateway
#aws
AgentCore Gateway supports OAuth 2.0, IAM, and API keys natively, but a request Lambda interceptor enables legacy Basic Auth integration. The interceptor validates the inbound JWT, retrieves system credentials from Secrets Manager, and constructs the Basic Auth header before forwarding to the downstream tool.
https://aws.amazon.com/ru/blogs/security/implement-custom-authentication-for-tools-integration-using-request-lambda-interceptor-in-agentcore-gateway
#aws
❤1👍1🔥1
This blog describes the methodology that powers a Mandiant internal tool for point-in-time AI vulnerability discovery. It has discovered hundreds of vulnerabilities in customer codebases and resulted in dozens of vendor notifications with either assigned or pending CVE numbers.
https://cloud.google.com/blog/topics/threat-intelligence/staying-ahead-of-adversarial-ai-through-agentic-source-code-review
#gcp
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
❤1👍1🔥1
Anthropic's stage-by-stage playbook for the AI-native SDLC: how teams plan, design, build, test, deploy, and maintain software with Claude.
https://claude.com/blog/the-ai-native-sdlc-playbook
#AI
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
❤1👍1🔥1
Practical LLM evaluation lessons from GitHub secret scanning: define product goals and guardrails first, treat offline evaluation as repeatable integration testing, keep eval data close to production, audit labels, use error analysis, and apply LLM-as-judge for human review triage.
https://github.blog/ai-and-ml/llms/how-to-evaluate-llms-before-production
#AI
Please open Telegram to view this post
VIEW IN TELEGRAM
❤2👍1🔥1
🔶 Detecting multi-stage attacks on AWS: A guide to cross-service signal correlation
A guide to detecting multi-stage AWS attacks by correlating signals across CloudTrail, VPC Flow Logs, and Route 53 DNS logs. Covers four business-context-aware patterns: unexpected S3 access, abnormal role chains, KMS key misuse, and off-hours privileged changes, with CloudWatch Logs Insights queries and Lambda automation.
https://aws.amazon.com/ru/blogs/security/detecting-multi-stage-attacks-on-aws-a-guide-to-cross-service-signal-correlation
#aws
A guide to detecting multi-stage AWS attacks by correlating signals across CloudTrail, VPC Flow Logs, and Route 53 DNS logs. Covers four business-context-aware patterns: unexpected S3 access, abnormal role chains, KMS key misuse, and off-hours privileged changes, with CloudWatch Logs Insights queries and Lambda automation.
https://aws.amazon.com/ru/blogs/security/detecting-multi-stage-attacks-on-aws-a-guide-to-cross-service-signal-correlation
#aws
❤1👍1🔥1
🔶 From clickops to governed IaC: CloudFormation drift detection in practice
A guide for migrating ClickOps-managed AWS infrastructure to governed CloudFormation IaC using IaC Generator for template generation, stack organization by lifecycle/ownership, and automated drift detection via EventBridge for continuous compliance monitoring.
https://aws.amazon.com/ru/blogs/devops/from-clickops-to-governed-iac-cloudformation-drift-detection-in-practice
#aws
A guide for migrating ClickOps-managed AWS infrastructure to governed CloudFormation IaC using IaC Generator for template generation, stack organization by lifecycle/ownership, and automated drift detection via EventBridge for continuous compliance monitoring.
https://aws.amazon.com/ru/blogs/devops/from-clickops-to-governed-iac-cloudformation-drift-detection-in-practice
#aws
❤1👍1🔥1
⛓️ Rust Supply Chain Attack on arrayref: Significant Overlap with DPRK Campaigns
Malicious versions of the arrayref Rust crate (and others) executed a backdoor at compile time. The campaign's infrastructure overlaps with recent DPRK supply chain attacks, including Mastra and axios.
https://www.wiz.io/blog/rust-supply-chain-attack-on-arrayref-significant-overlap-with-dprk-campaigns
#SupplyChainAttack
Malicious versions of the arrayref Rust crate (and others) executed a backdoor at compile time. The campaign's infrastructure overlaps with recent DPRK supply chain attacks, including Mastra and axios.
https://www.wiz.io/blog/rust-supply-chain-attack-on-arrayref-significant-overlap-with-dprk-campaigns
#SupplyChainAttack
❤1👍1🔥1
🔶 Password spraying campaign targets AWS root user accounts across 150+ organizations
Datadog Security Research observed a password spraying campaign targeting AWS root user accounts across 150+ organizations, attempting unauthorized authentication against these high-privilege accounts.
https://securitylabs.datadoghq.com/articles/aws-root-user-bruteforce-campaign
#aws
Datadog Security Research observed a password spraying campaign targeting AWS root user accounts across 150+ organizations, attempting unauthorized authentication against these high-privilege accounts.
https://securitylabs.datadoghq.com/articles/aws-root-user-bruteforce-campaign
#aws
❤1👍1🔥1
Microsoft Threat Intelligence examines attacks on exposed AI workloads, including LiteLLM gateway exploitation, credential harvesting, persistence, and cryptomining activity.
https://www.microsoft.com/en-us/security/blog/2026/08/26/when-ai-infrastructure-becomes-target-securing-gateways-control-points
#AI
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM
❤1👍1🔥1
A prompt injection flaw in Amazon Kiro IDE v0.7.45 allowing attacker-controlled repository content to exfiltrate sensitive data via the powersRecommendationUrl setting and Kiro Powers, exploitable in both trusted and untrusted workspaces.
https://mindgard.ai/blog/amazon-kiro-data-exfiltration
#AI
Please open Telegram to view this post
VIEW IN TELEGRAM
🔥3❤1👍1
🔶 Extend your data perimeter to the AWS Management Console with Private Access
AWS Management Console Private Access is now GA, routing all console traffic (auth, static assets, service APIs) through AWS PrivateLink VPC endpoints with no internet path required. VPC endpoint policies and Sign-In RCPs enforce identity, resource, and network perimeter controls on interactive console sessions.
https://aws.amazon.com/ru/blogs/security/extend-your-data-perimeter-to-the-aws-management-console-with-private-access
#aws
AWS Management Console Private Access is now GA, routing all console traffic (auth, static assets, service APIs) through AWS PrivateLink VPC endpoints with no internet path required. VPC endpoint policies and Sign-In RCPs enforce identity, resource, and network perimeter controls on interactive console sessions.
https://aws.amazon.com/ru/blogs/security/extend-your-data-perimeter-to-the-aws-management-console-with-private-access
#aws
❤1👍1🔥1