OSSQuesmaOrg/BinaryAudit — AI Binary Backdoor Detection BenchmarkGitHub·high signalXBlueskyLinkedInCopy link33 tasks, 17 models. Claude Opus 4.6 leads at 49%. Hidden backdoors in real servers. Ghidra + AI agent workflow.SourceSource pageGitHub↳ Follow the threadPolicy dependency / Stack layerA replay of 68,266 real Claude Code requests says plain LRU beats the clever KV-cache policiesGitHubStack layer / Update threadTip: Anthropic's own CI proves `claude plugin test` is not in a released build yetGitHubStack layer / Threat patternGemini CLI ships an external-context processor to stop indirect prompt injection through build filesGitHubStack layerAnthropic published `mods/`, the source of Claude Code's built-in plugins, and with it a second plugin architectureGitHubPolicy dependency / Stack layergit-ai is a Git extension that tracks which code in your repo was AI-generated, at 140 open PRs to 71 issuesGitHub TrendingPolicy dependency / Stack layerTraceCrate v0.2 reads Claude Code, Codex and OTLP traces in one local workbenchGitHubStack layer / ContrastAlibaba's open-code-review shipped v1.12.1 today and claims 4.7x the precision of Claude Code at a fourteenth of the tokensGitHub TrendingContrastTip: `claude plugin test` is a separate command from `claude plugin eval`, and it runs your hooks against the real engineGitHub