ClawHub
Back to skill

Security audit

presentation-by-html

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only presentation-building skill with no evidence of hidden access, persistence, credential use, or unrelated behavior.

This appears safe for normal presentation-building use. Review generated presentation files before sharing, especially if you include private screenshots, internal metrics, demo videos, or company-specific details.

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
92% confidence
Finding
The manifest description includes broad activation language such as 'or any scenario requiring structured visual storytelling for an audience,' which can cause the skill to trigger for a wide range of loosely related requests. Overly broad routing increases the chance the agent invokes this skill in unintended contexts, leading to incorrect behavior, prompt hijacking surface expansion, or interference with more appropriate specialized skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.