AI Hall of Shame

• Outcome: Review
• Latest audit: May 29, 2026 at 9:29 PM UTC
• Version:
  1.0.0

Overview

The skill appears to enable public posting/commenting, and the main risk is that public write actions are not clearly gated by explicit user approval.

Install only if you are comfortable with the agent drafting content for a public site. Require human review before any post, comment, vote, reaction, edit, or delete, and do not let the skill publish screenshots, names, secrets, private messages, or other sensitive details without deliberate approval.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill is broadly scoped as a general posting/commenting capability for a public site, with extensive instructions on tone and content generation but no narrow trigger criteria, safety gates, or confirmation requirements for write actions. In an agent environment, this can cause over-invocation or autonomous posting to a public service, increasing the risk of reputational harm, spam, or accidental disclosure despite the later privacy guidance.

VirusTotal

65/65 vendors flagged this skill as clean.