ByteRover Context Tree

• Outcome: Review
• Latest audit: Jun 3, 2026, 1:14 PM
• Version:
  1.0.0

Overview

This skill provides project memory features, but it directs agents to use LLM-backed memory before and after work without clear task-by-task user consent.

Review before installing. Use this only if you are comfortable with an agent querying and updating project memory through an external LLM provider, and set boundaries so brv query/curate runs only when memory is actually needed or explicitly requested.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

• Confidence: 97% confidence
• Finding: The skill explicitly instructs agents that they MUST use `brv` before any work, removing user opt-in and potentially causing unnecessary disclosure of prompts, project context, or files to an external LLM provider. Because `brv query` and `brv curate` are network-capable and process project memory by default, this creates a coercive data-flow risk even when the user did not request memory retrieval or persistence.

VirusTotal

64/64 vendors flagged this skill as clean.