ClawHub

improve-hn-karma

Security checks across malware telemetry and agentic risk

Overview

This skill drafts manual Hacker News comment plans for karma-building, with no code execution, credentials, or automatic posting, but users should review it for platform-ethics fit before use.

Install only if you are comfortable using an agent to draft public Hacker News comments for reputation-building. Review each draft manually, avoid spam or coordinated manipulation, and consider asking for preview-only output instead of saving a karma plan file.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases are broad and include generic requests like 'write HN posts' and 'compose HN replies', which can activate the skill during normal writing assistance rather than only when the user explicitly wants this automation. In this skill's context, that is more dangerous because the workflow is optimized to manipulate platform engagement and produce ready-to-post comments, so accidental invocation can steer benign requests into deceptive or spam-adjacent behavior.

Missing User Warnings

Low
Confidence
80% confidence
Finding
The skill instructs the system to write a dated markdown plan containing generated comments and posting guidance, but the description does not warn the user that a persistent artifact with ready-to-post content will be created. This reduces user awareness and consent, and in this context the file is specifically designed to facilitate coordinated reputation-building activity, which increases the chance of misuse or unintended posting.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal