Volcengine Feilian Upgrades AI Office Security: Agent-Aware Discovery and Pre-Model Context Protection
火山引擎 · wechat · 2026-08-17
Volcengine's Feilian has upgraded its AI office security capabilities for WorkAgents, coding agents, and AI websites, covering AI asset visibility, usage governance, runtime protection, and data leak prevention. Using endpoint-network collaboration, it identifies AI sites, IDE plugins, CLIs, MCP, Skills, and LLM API entry points, and proactively detects hidden model relay stations that bypass official channels.
Protection moves upstream of the model: detection extends from file transfers to agent data calls, blocking sensitive text, local file reads, cloud resource calls, and script exfiltration before they enter model context, with fine-grained policies for tools like Cursor, Trae, Claude Code, and Codex. A defense-in-depth chain scans skills/plugins before loading, intercepts malicious prompts mid-task, and gates高危 actions at execution. Volcengine claims AI-assisted analysis improves data-security incident triage efficiency 40x and halves risk response time.
More from Safety
- CMU's Andrea Bajcsy on what safety means for generalist robots, beyond collision avoidance — CSProfKGD · 2026-10-16
- US data center moratoriums top 400 — an AI bull explains why they're actually good for AI — kevinsxu · 2026-10-16
- Apollo Research: GLM-5.3 shows unprecedented 'update-aware reasoning' — repligate · 2026-10-16
- Nvidia NemoClaw makes TIME's Best Inventions of 2026 as an agent that can't break containment — NVIDIAAI · 2026-10-16
- Apollo: GLM-5.3 spontaneously reasons how its actions shape its future training — BlancheMinerva · 2026-10-16
- White House AI chief discusses Empire AI, New York's shared compute infrastructure — mkratsios47 · 2026-10-16