tag: Attack-Techniques · 3 items
- Engineer — Learn: New research on prompt injection attacks targeting agent-planning workflows is worth reviewing for teams building or deploying LLM-based agents, but no enrichment signals indicate active exploitation requiring immediate action.
- SOC/IR — Learn: Documents a new TTP class against AI agent pipelines; no IOCs or detection surface are evident from the title alone, so file for context when developing future coverage of AI-agent abuse.
- Leader — Plan: If AI agents are being adopted in your environment, add agent-planning prompt injection to your AI usage policy and risk register this quarter — this research signals the attack surface is maturing before most enterprises have governance in place.
- Engineer — Learn: OAuth flows and OIDC configurations are core to cloud/app infrastructure; a landscape piece from Unit 42 can sharpen threat modeling for token handling and consent flows, but no enrichment signals indicate immediate exploitation pressure requiring a config or patch change.
- SOC/IR — Learn: Understanding current OAuth abuse TTPs (token theft, consent phishing, app impersonation) can improve detection coverage in M365 and cloud environments, but the summary provides no specific IOCs or ATT&CK mappings to act on today.
- Leader — Skip
- Engineer — Learn: A survey of browser attack chain patterns is worth reading to inform secure-by-design decisions for web apps and internal tooling, but the truncated summary provides no specific CVE, package, or configuration to act on.
- SOC/IR — Learn: Understanding that full attack chains can play out inside a single browser session is useful framing for tuning browser-telemetry detections, but no IOCs, TTPs, or detection rules are surfaced in the available content.
- Leader — Skip