ClawHub

context-engineer

Security checks across malware telemetry and agentic risk

Overview

This is a local context-auditing tool that behaves as described, but its reports and snapshots may reflect sensitive workspace or config data.

Use this on workspaces and config files you intend to audit. Treat terminal output and saved snapshots as potentially sensitive because they can reveal file paths, token counts, tool names, and other details derived from private prompts, memories, or configuration.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding
The skill advertises executable commands that read workspace files, inspect configuration, and write snapshot outputs, but it does not declare corresponding permissions. This creates a trust and containment gap: a host may treat the skill as low-privilege based on metadata while the documented behavior clearly requires file read, file write, and likely environment access, increasing the chance of unauthorized data exposure or unintended modification when invoked.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal