Counter Evidence Hunter

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:30 PM UTC
• Version:
  2.0.0

Overview

This is an instruction-only skill for challenging an existing conclusion with counter-evidence, with no code, credentials, persistence, or hidden actions.

Install this if you want an agent to pressure-test conclusions before important analysis. Avoid giving it confidential claims or private business details when search tools are enabled, because the workflow may turn those details into search queries.

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: 91% confidence
• Finding: The trigger conditions are very broad ('after any mainline judgment', 'before high-risk conclusions', 'before risk analysis'), which can cause the skill to be invoked in many loosely related contexts without clear gating. In an agent pipeline, this increases prompt-surface area, can create unnecessary tool/skill chaining, and may distort workflows by inserting speculative counter-narrative generation where it is not needed.

VirusTotal

65/65 vendors flagged this skill as clean.