ClawHub
Back to skill

Security audit

deep-digest

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a text-analysis helper that may handle sensitive user-provided content, but the evidence does not show hidden access, persistence, exfiltration, or unsafe execution.

Install only if you are comfortable using it on text you intentionally provide. Avoid pasting secrets, credentials, private conversations, medical/legal/financial details, or confidential business material unless you have reviewed and redacted it first.

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 activation conditions are very broad ('any text input', chat logs, notes, articles, research material), which can cause the skill to trigger in many contexts where users did not intend deep analysis or disclosure. In practice this increases the chance that sensitive conversational, personal, or business content is processed unnecessarily, expanding privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly invites processing of chat logs, notes, conversations, and diaries, all of which commonly contain sensitive personal, confidential, or regulated information, but provides no warning or handling guidance. This omission can lead users or downstream agents to submit secrets, personal data, or internal business material without informed consent or minimization.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal