ClawHub

AI C-Suite

Security checks across malware telemetry and agentic risk

Overview

This skill runs local Python scripts to generate business decision notes, with no evidence of hidden network access, credential use, or destructive behavior.

Install only if you are comfortable running local Python scripts that read business context and write decision memos. Use redacted data for testing, keep config/company.local.yaml and logs private, and avoid committing generated files that contain pricing, runway, strategy, or internal decisions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The README explicitly tells users to place real company data into a local YAML file and then generate decision artifacts under logs/, but it does not warn that these outputs may contain sensitive business information such as pricing strategy, runway, ARR/MRR, constraints, and internal decisions. While this is not an exploit by itself, it creates a real confidentiality risk because users may unintentionally retain, commit, or share sensitive files produced by the skill.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The invocation guidance is broad enough to match a wide range of common business requests, which can cause the skill to activate in contexts where users did not intend script-backed execution. Because the skill allows Bash and performs file writes, over-broad triggering increases the risk of unnecessary local command execution and modification of workspace files, even if the underlying scripts are not overtly malicious.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal