ResearchPrompt Injection Attacks on Agentic Coding Assistants SoK 78 StudiesarXiv·high signalXBlueskyLinkedInCopy linkFirst comprehensive systematization across 78 studies. Attack success rates exceed 85% against SOTA defenses. 42 distinct attack techniques cataloged. Architectural mitigations required.SourceSource pagearXiv↳ Follow the threadStack layer / Threat patternSRE-Bench: 5,000 expert hours to build the first contamination-free reverse-engineering benchmark, and frontier agents solve only 31.5% of itarXivStack layer / Threat patternHARD: let the agent evolve its own runtime defenses instead of hand-writing guardrailsarXivStack layer / Threat patternHARD Turns LLM Agent Runtime Defense Into a Self-Evolving Loop Instead of Hand-Written RulesarXiv 2608.12977Stack layer / Threat patternIterative LLM Infrastructure-as-Code Repair Silently Breaks Security Checks in 3.3% of Scenarios; Stop at Iteration 3arXiv 2608.13404Policy dependency / Stack layerBuild Integration, Not Fuzzing, Is What Kills LLM Dynamic Analysis on Real Autonomous-Vehicle StacksarXiv 2608.13450Policy dependency / Stack layerExport Controls Turn Frontier Model Access Into a Cyber-Defence Dependency for Middle PowersarXiv 2608.13272Policy dependency / Stack layer59.4% of Telegram Mini Apps Contact Undisclosed Third Parties and None Offer Opt-OutarXiv 2608.13390Threat pattern / ContrastVertical Federated Learning Backdoor Results Collapse Under Realistic Constraints; BVBench Released to Reset the FieldarXiv 2608.12962