ClawHub
Back to skill

Security audit

Medical Research Literature Reader Pro

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only medical literature review skill with no code, install steps, credential use, persistence, or hidden data flow.

Reasonable to install for paper analysis. Treat outputs as research assistance, not medical advice, verify cited studies before relying on them, and avoid pasting PHI, private patient details, or unpublished confidential research unless you have permission.

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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger description is broad enough to capture many generic research-assistance requests such as summarization, critique, and interpretation tasks, which can cause the skill to activate outside its intended niche. Over-broad routing can lead to inappropriate tool/skill selection, user confusion, and accidental processing of inputs under a more specialized workflow than warranted.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The plugin activation rule is broad enough that an agent may load or suggest plugins based on vague cues rather than explicit user intent. In a medical literature-reading skill, this can cause scope creep, unnecessary processing, and increased exposure to downstream prompt-injection or misleading output formatting from auxiliary plugin content, even if the file itself does not contain overtly malicious instructions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.