ClawHub

Reveal Reviewer skills

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Reveal review assistant, but users should be careful because it can browse sites and submit findings, screenshots, notes, or videos to Reveal using their API key.

Install only if you intend to let an agent perform Reveal review workflows. Keep the Reveal API key private, review the agent-browser dependency separately, avoid reviewing pages that contain personal or confidential data, and check the structured findings and screenshots before approving final submission.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description includes broad trigger phrases like reviewing products, testing apps, submitting feedback, checking tasks, and earning rewards, which can overlap with many ordinary user requests. This can cause the agent to invoke the skill in situations the user did not explicitly intend, leading to unintended browsing, external API calls with the user's API key, and possible submission workflows against third-party services.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The API reference explicitly instructs the agent to make authenticated requests to an external service and upload screenshots/video evidence, but it provides no requirement for user notice, consent, or data-minimization guidance. In this skill context, the agent is expected to browse third-party sites and capture observations, so the risk is heightened because screenshots, notes, and recordings may contain sensitive user or site data that gets transmitted off-platform without clear safeguards.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal