ClawHub

Academic Deep Research

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed deep-research workflow whose web, memory, and parallel-session use fits its purpose and is gated by user checkpoints.

Install this if you want a structured, source-heavy research assistant. Avoid giving it secrets, regulated data, confidential business plans, or private personal information unless you are comfortable with that context being used in web searches, fetched-source analysis, memory lookup, or parallel research sessions.

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
91% confidence
Finding
The trigger phrases are broad enough to match ordinary user requests such as asking for an analysis, literature review, or broad explanation, which can cause the skill to activate outside its intended niche. In an agent platform, overly broad activation increases the chance of prompt hijacking of normal conversations, unnecessary tool use, and unintended delegation to a more privileged workflow.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation conditions are ambiguous because they rely on generic task descriptions like 'deep research,' 'exhaustive analysis,' or 'claims need verification from multiple sources' without defining clear thresholds. This creates routing ambiguity that can let the skill capture a wide range of benign conversations, expanding attack surface and potentially invoking web access and parallel sessions when the user did not clearly request that behavior.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal