AgentsClawSec — Agent-Native Security Monitoring by Prompt Security SentinelOneSentinelOne·high signalXBlueskyLinkedInCopy linkFirst security suite running inside the agent. SOUL.md drift detection, NVD CVE polling, automated audits, SHA256 checksum verification.SourceSource pageSentinelOne↳ Follow the threadStack layer / Threat patternClaude Code adds a Containment Escape rule to auto mode and blocks plugin symlink path escapesGitHub (anthropics/claude-code)Stack layer / Threat patternpydantic-ai 2.37.0 adds glm-5.3-flash and maps Z.AI's non-standard finish_reason valuesGitHubStack layer / Threat patternCline Desktop v0.0.22 imports your Claude Code, Codex and opencode history as resumable Cline sessionsGitHubStack layer / Threat patternHeretic's name now appears inside Hugging Face model IDs, turning an abliteration tool into a distribution labelGitHub TrendingPolicy dependency / Stack layerUnsloth 0.1.805-beta doubles Qwen3.8-Flash-Next and GLM-5.3-Flash inference with MTP on by defaultGitHubStack layer / Threat patternToolJet, a 40.8k-Star Retool Alternative, Shipped an MCP Server That Builds Apps Without CodegenToolJet (Show HN)Policy dependency / Stack layerA Show HN MCP Proxy Puts Policy Where the Model Cannot Reach ItGitHub (Show HN)Stack layer / Threat patternCIPR: how you phrase a request changes whether a poisoned repo compromises your coding agentarXiv