ClawHub

Message Clinic Runner

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed writing workflow that reads a supplied draft, runs a structured rewrite process, and saves one output file.

Safe to install for structured draft-rewriting workflows. Review the dependent BookForge skills if they are also installed, and avoid using confidential drafts unless your agent workspace and model provider are appropriate for that content; expect a file named message-clinic-output.md to be created.

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 list is extremely broad and includes generic phrases like 'rewrite this message', 'improve this draft', and 'just fix it', which can cause the skill to activate in situations far outside its intended specialized workflow. This creates prompt-routing risk: the agent may invoke a heavy rewriting/orchestration skill unexpectedly, causing inappropriate transformations, unnecessary file writes, or bypass of a more suitable narrower skill.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The when_to_use section uses vague trigger conditions and insufficient exclusions, which increases the chance of incorrect autonomous selection of this skill. In an agentic environment, poor routing is a real security and safety issue because the wrong skill can read inputs, invoke dependencies, and generate persistent outputs without the user's informed intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal