ClawHub
Back to skill

Security audit

Reply And Comment Writer

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed social engagement drafting helper that reads brand voice context and keeps posting under human control.

Installers should understand that the skill may read brand voice/profile context to draft social replies. It does not pull comments or DMs, does not post for the user, and explicitly refuses mass automation or fake engagement; users may still want a clearer trigger than "help me engage" to avoid accidental activation.

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 (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrase "help me engage" is broad, natural-language wording that can appear in many ordinary conversations, making accidental invocation plausible. In this skill’s context, unintended activation could cause the agent to enter an engagement-writing workflow, read additional brand context files, and produce social-response guidance when the user did not explicitly request that behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.