ClawHub
Back to skill

Security audit

Morfeo Content Pipeline

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent social-video pipeline, but it includes moderation-workaround guidance and recurring automated social-content generation that users should review before installing.

Review before installing. Use only with brand assets and social accounts you are authorized to use, remove the moderation-workaround instructions, inspect the referenced runtime project and scripts, and add explicit credential scopes, opt-in scheduling, stop controls, logs, and human approval before drafts are posted.

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)

Ssd 2

Medium
Confidence
98% confidence
Finding
The instruction to write prompts in English specifically to avoid Gemini moderation is an explicit moderation-evasion pattern. Even if intended to reduce false positives, it normalizes bypassing provider safety controls and can enable generation of content that would otherwise be blocked or more carefully reviewed.

Ssd 2

Medium
Confidence
98% confidence
Finding
This known-issues note reinforces a semantic moderation-bypass technique by recommending switching languages when specific wording triggers moderation. Recommending systematic rephrasing to defeat safeguards increases the chance that unsafe or policy-disallowed generations will slip through.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.