ClawHub
Back to skill

Security audit

Newsletter SEO Pipeline

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed newsletter and blog SEO workflow that reads local article/project files, runs local validation scripts, and writes a paste-ready output file.

Install if you want an SEO article pipeline and are comfortable with it reading project style/memory files and article drafts, running the included Python helper scripts, and creating a local paste-ready Markdown file. Use trusted companion skills and project folders, and check the target article path before running.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs the agent to read project files such as `projects/<slug>/writing-style.md` and `projects/<slug>/project.md`, and to create or modify article outputs plus generated `-PASTE.md` files, but it does not declare any permissions. Hidden or undeclared file read/write behavior weakens reviewability and consent, and can lead to unintended access to workspace files when the skill is triggered.

Vague Triggers

Medium
Confidence
87% confidence
Finding
Broad triggers like 'write article', 'write blog post', and 'write newsletter' can cause the skill to auto-activate for ordinary writing requests, pulling the agent into a multi-step pipeline with file access and script execution that the user may not have intended. Over-broad invocation increases the chance of surprise file operations, incorrect workflow selection, and misuse in contexts lacking required parameters.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.