ByteRover

ByteRover 3.1.0 adds fast file-based search alongside LLM-powered query. - New: Added brv search for ranked, BM25-based keyword search across context-tree files, with JSON output and filtering options. No LLM required. - All major commands are now clearly organized for structured automation and natural-user workflows. - brv search enables agents to quickly locate files for downstream tasks or pipeline integration, reducing latency and LLM usage. - Documentation reorganized to clarify when to use search vs. query. - No breaking changes to existing query, curate, review, locations, or version control functionality.

暂无更新说明。

暂无更新说明。

暂无更新说明。

OpenClaw 分析

The skill's purpose and instructions are coherent for a local knowledge-management helper, but it directs installing an external npm CLI and implies sending project data to a default remote LLM provider with no clear disclosure or provenance — which could expose project files or secrets.

置信度: medium

VirusTotal

Type: OpenClaw Skill Name: byterover Version: 3.1.0 The skill bundle promotes the use of an external CLI tool (`byterover-cli`) and a third-party service (byterover.dev) for 'AI knowledge management.' It instructs the agent to send project context and source files to a remote LLM provider that requires no API key by default, which poses a significant data exfiltration risk. While the documentation claims data is only sent to servers during a `vc push`, the `query` and `curate` commands rely on a cloud-based LLM provider, creating a contradiction regarding data privacy. The forceful instructions in `SKILL.md` requiring the agent to use the tool 'before any work' increase the risk of sensitive project data being uploaded to an unverified third-party service.