ClawHub
Back to skill

Security audit

Workspace Indexer

Security checks across malware telemetry and agentic risk

Overview

This skill is a workspace index generator that matches its stated purpose, though the index it creates may contain private project and runtime details.

Install this only in workspaces you are comfortable indexing. Review WORKSPACE_INDEX.md before committing or sharing it because it may include project names, memory references, ports, container IDs, and cleanup/status notes. Enable daily HEARTBEAT maintenance only if you want recurring automatic updates.

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 (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly writes or updates `WORKSPACE_INDEX.md` but does not warn the user that it will modify files in the workspace. Hidden write behavior is risky because it can cause unintended state changes, overwrite existing documentation, or create persistent artifacts without informed user consent.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs the agent to scan the workspace, read directory documentation, search memory, and check running services or containers, yet it omits a privacy/system warning about this broad environmental inspection. This can expose sensitive project names, operational metadata, memory contents, and service details that users may not expect to be enumerated or summarized.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The description is overly broad and implies automatic, intelligent behavior without clearly bounding when the skill should run or what directories it may touch. In combination with powerful tools like exec, read, write, and memory_search, this can cause the agent to invoke the skill in unintended contexts, leading to unnecessary filesystem access, modification, or data indexing beyond the user's intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.