Ai Company Cmo 3.0.0

Security checks across malware telemetry and agentic risk

Overview

This appears to be a marketing strategy skill, but it requests broad file, API, and cross-agent authority without enough concrete limits.

Review this skill before installing in a real workspace. Use least-privilege limits, require explicit confirmation before file writes, API calls, or cross-agent messages, and verify the intended published version because the included metadata and review notes are inconsistent.

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
90% confidence
Finding
The manifest includes several broad generic triggers for common marketing concepts, increasing the chance this skill activates during ordinary conversation rather than explicit invocation. Because the skill has read/write file access, network API access, and MCP capabilities, unintended routing could expose user context to a skill that was not deliberately selected.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal