ClawHub

SagaSmith Module Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a D&D adventure-module generator that writes generated campaign content to local module files and imports it into a D&D module tool, with no evidence of hidden or malicious behavior.

Installers should expect this skill to create or append files in a workspace modules folder and to use a D&D module import/index workflow when available. Before using it in a workspace with existing campaign files, ask the agent to confirm target filenames and avoid overwrites unless explicitly approved.

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 manifest description uses very broad trigger language such as 'create, generate, or make' a new adventure, module, or campaign setting, which can cause the skill to activate for generic creative-writing requests beyond the user's specific intent. Over-broad activation can route unrelated requests into a workflow that performs file writes and tool-driven imports, increasing the chance of unintended side effects.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill's core rule says to always write to `<workspace>/modules/<name>.md` first and later discusses deleting and re-importing existing modules, but the main workflow does not require explicit user confirmation before file creation or overwrite-sensitive operations. In an agent environment, this can lead to unintended file modification, clobbering of prior content, or destructive re-import behavior triggered by an overly eager activation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal