ClawHub
Back to skill

Security audit

Triple Whale

Security checks across malware telemetry and agentic risk

Overview

This appears to be a purpose-aligned Triple Whale integration skill, with one broad trigger wording issue users should understand before use.

Install this if you want an agent to help with Triple Whale tasks. Before using it, make sure requests involving Triple Whale are explicit, and review any connector permissions or credentials so the agent only accesses the Triple Whale accounts and data you intend.

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
88% confidence
Finding
The trigger instruction is extremely broad: it says to use this skill for ANY Triple Whale request and whenever a task involves Triple Whale. This can cause the agent to invoke the skill on casual mentions or ambiguous requests, increasing the chance of unintended external data access or unnecessary connector execution without sufficiently verifying user intent.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.