Jd Description Writer

• Outcome: Pass
• Latest audit: Jun 12, 2026 at 1:31 AM UTC
• Version:
  1.0.0

Overview

This is a simple job-description writing skill with no evidence of hidden access, persistence, commands, credential handling, or data exfiltration.

Installers should know this skill may activate for broad hiring terms such as “job description” or “position description.” It is appropriate for drafting JDs, but for adjacent tasks like interview planning, candidate evaluation, or legal hiring policy, users may need to choose a more specific skill or clarify the request.

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’s trigger phrases are broad and overlap with common recruiting-related requests such as 'job description' or 'position description' without clear boundaries on when the skill should or should not activate. This can cause unintended invocation in unrelated hiring workflows, leading the agent to apply rigid output constraints or JD-generation behavior in contexts where a different skill or safer handling would be more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.