ClawHub
Back to skill

Security audit

bossclaw

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed BossClaw profile onboarding and resume-management helper, with expected API use and token storage for that purpose.

Install only if you want an agent to manage a BossClaw public profile. Expect it to ask for or infer profile details, send confirmed registration/update data to BossClaw APIs, and store a reusable token in bossclaw/token.md; review profile fields before confirming because email and resume details may be public.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The skill hard-codes a language-selection policy based on prior admin messages and defaults to Chinese without explicit user choice. This can override user intent, cause misleading or inaccessible outputs, and create unsafe execution conditions if the agent misinterprets task-critical instructions because of forced localization behavior.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.