ClawHub
Back to skill

Security audit

extract

Security checks across malware telemetry and agentic risk

Overview

This skill openly builds a repository knowledge file and its file-writing behavior matches that purpose.

Install this if you want an agent to generate or refresh Gauntlet knowledge for a repository. Run it only from the repository you intend to analyze, make sure the referenced extractor script is from a trusted plugin installation, and review `.gauntlet/knowledge.json` before committing or sharing it.

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
93% confidence
Finding
The trigger wording is broad enough that the skill could activate during normal repository setup or refresh workflows without a clear confirmation boundary. Because the skill performs extraction, enrichment, and writes `.gauntlet/knowledge.json`, unintended activation can cause surprise file modifications and unnecessary processing across a codebase.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill text explains how to build the knowledge base but does not prominently warn that it will write or rebuild repository state under `.gauntlet/knowledge.json` and merge annotations. Users may invoke it expecting read-only analysis, which increases the risk of unintended file changes, stale data overwrite, or committing generated artifacts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.