ClawHub

Sales Enablement

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only sales enablement skill with coherent templates and only a scoped, disclosed read of local product-marketing context.

Installers should treat this as a low-risk content-generation skill. Before using it, review any `.agents/product-marketing-context.md` or `.claude/product-marketing-context.md` file in the workspace and avoid putting secrets, credentials, or unapproved confidential claims there, because the skill may use that context in generated sales collateral.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill description contains a very broad set of trigger phrases such as 'sales materials,' 'help my sales team,' and 'what should I give my sales reps,' which can overlap with adjacent domains like marketing, pricing, revops, or competitor analysis. This can cause the agent to invoke the skill in unintended contexts, increasing the chance of mismatched guidance, over-collection of context files, or use of the wrong workflow for a user request.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The eval explicitly rewards activation on vague, casual phrasing ('i need a one-pager... something that summarizes our product') rather than requiring clearer sales-enablement intent. Overly broad trigger expectations can cause the skill to activate in contexts where a general assistant response would be safer or more appropriate, increasing misrouting and unintended behavior across unrelated user requests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal