ClawHub

Account Research

Security checks across malware telemetry and agentic risk

Overview

This account-research skill appears useful but may access sensitive CRM or contact-enrichment data from a broad natural-language prompt without enough user-facing privacy controls.

Install only if you are comfortable with the skill querying connected enrichment or CRM systems for account research. Prefer configuring least-privilege connectors, requiring explicit confirmation before CRM/enrichment lookups, and limiting display of personal contact details and internal notes by default.

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 (3)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger phrase "tell me about [company]" is broad enough to overlap with ordinary conversation, which can cause accidental invocation of the skill in contexts where the user did not intend account research. Because this skill can automatically use web search and optionally connected enrichment or CRM systems, unintended activation could surface sensitive business or contact data more readily than a narrower trigger would.

Vague Triggers

Low
Confidence
73% confidence
Finding
The example "Tell me about [company] before my call" reinforces a loose invocation pattern that lacks clear boundaries, increasing the chance the skill is triggered from common natural-language requests. In this skill's context, even a low-friction accidental trigger can expose CRM history, relationship notes, or enriched contact details if connectors are enabled.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The connector section describes enrichment and CRM capabilities but does not clearly warn users that using those connectors may access and display sensitive personal, contact, and relationship data. This lack of transparency can lead users to invoke the skill without understanding the data exposure implications, especially when verified emails, phone numbers, and internal CRM notes may be surfaced.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal