ClawHub
Back to skill

Security audit

Knowledge Digest

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a courseware/study-material helper with some transparency issues around optional web research, but no evidence of destructive, deceptive, or credential-seeking behavior.

Install if you want a study/courseware assistant, but specify when it should use only your supplied materials. If it researches the web, review and verify sources before relying on the generated lessons, quizzes, or slides.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The skill expands from transforming user-provided materials into independently searching for and compiling external sources when no source is supplied. This broadens data access and behavior without an explicit consent boundary in the manifest, creating a scope-creep risk where the agent may fetch untrusted or unexpected content and present it as courseware.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger phrases are broad enough to match many ordinary study-related requests, which can cause the skill to activate in contexts where the user did not intend document conversion or asset generation. Over-broad invocation increases the chance of unexpected file generation, tool use, or web-search behavior being initiated under ambiguous prompts.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill description does not warn users that, absent source material, it may search the web and collect external information. This undermines informed consent and transparency, especially in an educational setting where users may assume outputs are derived only from uploaded textbooks rather than third-party sources.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.