ClawHub
Back to skill

Security audit

Agent Pipeline

Security checks across malware telemetry and agentic risk

Overview

This is a coherent coding-workflow skill, but it asks agents to broadly share an auth profile and always send task updates to a board service without enough scoping or user control.

Review before installing. Use only in a trusted development environment, replace blanket auth-profiles.json copying with per-role or temporary credentials, and confirm the board endpoint, planner target, repository, branch, and push behavior before allowing the workflow to run.

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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs all agents to copy `auth-profiles.json`, which appears to be a shared credential-bearing file, without any scoping, least-privilege controls, or warning about secret handling. This expands credential exposure across multiple spawned agents and increases the chance of leakage through logs, prompts, artifacts, or compromise of a less-trusted sub-agent.

Missing User Warnings

Low
Confidence
89% confidence
Finding
The skill mandates board logging to an HTTP endpoint on an internal network and says to log before, during, and after execution, but provides no warning that project details may be transmitted off-agent. This can leak sensitive task context, code-change summaries, branch names, or other internal information to an external service, especially because the logging is required rather than optional or consent-based.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.