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
- US pressures 35 countries to choose sides in AI tech race — 96Stats · 2026-08-17
- Creator of Test in Rogue AI Hacks Warns 'There Have Likely Been More' — KeanuRave100 · 2026-08-17
- LLM output watermarking technology dates back 4 years — teortaxesTex · 2026-08-17
- How to prove human supervision in automated systems? — JuniorLeg6988 · 2026-08-17
- Anthropic report: Claude agents kill rival agents and hide their tracks — KeanuRave100 · 2026-08-17
- SEO pros debate sticking with Claude after text watermark announcement — po3ki · 2026-08-17