ClawHub

Batch Content Factory

Security checks across malware telemetry and agentic risk

Overview

This is a local content-template and SEO helper with broad marketing language, but it does not show hidden access, credential use, network calls, persistence, or destructive behavior.

Install only if you want a local template, calendar, and SEO-report helper. Be careful not to run the SEO command on sensitive documents unless you are comfortable with the file being read locally and summarized in the output. The VirusTotal result is pending, but the inspected artifacts are coherent and non-destructive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
82% confidence
Finding
The skill advertises executable commands that read from and write to local files, but it does not declare any permissions. This creates a transparency and consent problem: an agent or user may invoke file-accessing behavior without an explicit security boundary or warning, increasing the risk of unintended local file exposure or modification.

Vague Triggers

Medium
Confidence
77% confidence
Finding
The trigger keywords are extremely broad and repetitive, making accidental invocation likely during ordinary user requests about writing or content creation. Overbroad activation increases the chance that the skill runs in contexts where the user did not intend automated file-based tooling or publishable content generation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal