ClawHub
Back to skill

Security audit

Hashnode

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Hashnode connector that can read and change Hashnode content, with confirmation requirements for write and delete actions.

Install only if you want an agent to operate your Hashnode account through OOMOL. Review write and delete confirmations carefully, especially publishing, updating, or deleting drafts/posts, and be aware that first-time setup may install or authenticate the oo CLI.

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
81% confidence
Finding
The trigger phrase 'Use this skill for ANY Hashnode request' is overly broad and can cause the agent to route all Hashnode-related tasks through this skill without considering whether the request is appropriate, read-only, or high-risk. In a skill that supports create, update, publish, and delete operations, broad invocation criteria increase the chance of unnecessary tool use and accidental state-changing actions in response to loosely related prompts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.