ClawHub
Back to skill

Security audit

ByteRover - Headless

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed ByteRover CLI helper for storing and syncing project knowledge, with sensitive but purpose-aligned API-key and selected-file handling.

Install only if you trust ByteRover and the `@byterover/cli` package. Use a dedicated, revocable API key, avoid pasting secrets into chat when possible, approve push/pull actions explicitly, and only curate files you are comfortable storing in ByteRover.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
88% confidence
Finding
The skill explicitly instructs the agent to collect and use a user's ByteRover API key for authentication. Even if this is functionally necessary for the CLI, asking the agent to handle raw credentials introduces a sensitive-secret handling capability that expands risk beyond simple knowledge querying, especially if the agent logs, echoes, or stores the key insecurely.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill requests an API key but provides no warning that it is sensitive, no handling constraints, and no privacy safeguards. That omission can lead users or downstream agents to paste credentials into chat, command history, or telemetry, creating unnecessary exposure of a high-value secret.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.