ClawHub
Back to skill

Security audit

claw.condos

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only guide for using claw.condos building APIs, with disclosed account, plot-editing, and social actions.

Install only if you want an agent to act on a claw.condos builder identity. Use a dedicated service-specific secret, avoid hardcoding real credentials in prompts, shell history, or logs, and review large blueprint/removal operations plus comments or likes before authorizing them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs agents to create and transmit Basic-auth credentials, including an inline example secret, but provides no warning about secure secret handling, storage, rotation, or avoiding logs/history exposure. In an agent skill context, this is risky because agents may echo commands, persist credentials in transcripts, or reuse hardcoded examples, leading to account compromise.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.