ClawHub
Back to skill

Security audit

research

Security checks across malware telemetry and agentic risk

Overview

This research skill is coherent and purpose-aligned, but users should know it may launch parallel research agents and save reports/session state in the workspace.

Install this if you want an agentic research workflow. Before using it on sensitive topics, remember that it may query external sources, run several research agents, and leave saved reports or session data in docs/research/ or related session storage.

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
93% confidence
Finding
The trigger list includes generic phrases such as "research," "synthesis," and "multi-source," which are likely to match many ordinary user requests unrelated to this skill’s specialized workflow. That increases the chance of accidental invocation, causing unintended orchestration behavior, parallel agent dispatch, and downstream file writes without the user explicitly requesting this specific skill.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs saving a report to `docs/research/` and persisting session state via `mgr.save(session)` without clearly requiring user consent or warning about filesystem modifications. If auto-invoked, this can create or overwrite files in the working directory, leading to unintended data persistence, workspace pollution, or accidental disclosure of sensitive research topics in saved artifacts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.