ClawHub
Back to skill

Security audit

FTM Copilot

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only IBM FTM assistant skill with broad activation wording but no hidden execution, credential access, persistence, or data exfiltration behavior.

Install this only if you want IBM FTM-specific help. Treat the included database, broker, MQ, Docker, and deployment commands as examples: verify the target system and use normal change controls before running anything in production financial infrastructure.

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

High
Confidence
98% confidence
Finding
The manifest description lists a very wide set of related technologies and concepts, then adds 'or any combination of these' and 'When in doubt, trigger,' which creates an ambiguous and expansive activation boundary. This can cause unintended invocation on general enterprise integration or payments discussions that only loosely relate to IBM FTM.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.