ClawHub
Back to skill

Security audit

Ceo Advisor 1.0.0

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a coherent CEO-advisory package with local reference material and disclosed local analysis scripts, not hidden or harmful behavior.

Install only if you want broad CEO-level strategic guidance. Review the Python scripts before running them and avoid entering sensitive company financials, investor details, or board materials unless you are comfortable processing that data locally in the agent context. Treat outputs as advisory drafts, not professional legal, financial, or governance advice.

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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill uses very broad activation language such as 'use when planning strategy' and many generic executive/business trigger terms, which can cause the agent to invoke this skill in situations where it is not the best fit. Over-broad invocation increases the chance of context hijacking, irrelevant guidance being injected into unrelated workflows, or accidental exposure to sensitive strategic or investor-related contexts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.