ClawHub
Back to skill

Security audit

WordPress Blog Publisher

Security checks across malware telemetry and agentic risk

Overview

This WordPress automation skill uses sensitive site credentials and can change live content, but the behavior is disclosed, purpose-aligned, and guarded by user-approval and dry-run instructions.

Install only if you are comfortable giving the agent WordPress application-password access. Use a dedicated least-privilege WordPress user, keep credentials in environment variables or a secret manager, do not commit config/sites.json, review dry-runs before --execute, and explicitly confirm any live publish/update, all-site batch, or remote media operation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation includes use of Basic authentication with a WordPress application password but provides no warning that these credentials are highly sensitive and grant site access. In an agent skill, this increases the risk of accidental credential exposure in prompts, logs, screenshots, or downstream systems, which could enable unauthorized content modification or broader account abuse.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.