ClawHub
Back to skill

Security audit

papers

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent academic paper search helper, with only a minor caution that some activation keywords are broad.

This is reasonable to install for literature review work. Be aware it may trigger on general PDF or paper-related requests, and only provide local PDF file paths that you actually want the agent or document-conversion tool to read.

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
96% confidence
Finding
The trigger list includes very broad terms like "academic," "papers," and "pdf," which are likely to appear in ordinary user requests unrelated to this specific skill. Over-broad activation can cause unintended invocation, expanding the skill’s reach and increasing the chance that its instructions or tool-use patterns are applied in contexts where they were not intended.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.