ClawHub
Back to skill

Security audit

Hugo Blog Publisher Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward blog publishing helper, but users should understand it can write blog files and run git push when used.

Install only if you want an agent to create blog files and push them with your configured git credentials. Review the resolved blog path, generated files, commit message, and remote before letting it publish, and avoid providing a callback URL unless you trust the destination and know what data will be sent.

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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly describes creating files and performing `git push` automatically, but it does not require an explicit user confirmation before making repository changes or transmitting them to a remote. In an agent context with `exec` and `write` permissions, this can cause unintended modification and publication of user content or repository state, especially if memory-derived paths are wrong or user input is misinterpreted.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The documented `callback_url` parameter implies network transmission of task status or content, but the skill provides no warning about what data may be sent, where it goes, or what trust boundaries apply. This creates a risk of silent exfiltration of article contents, repository information, or deployment metadata to attacker-controlled endpoints if the parameter is supplied or inferred.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.