raigo agent firewall

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:31 PM UTC
• Version:
  1.0.3

Overview

This is an instruction-only security policy skill; its broad claims may overstate protection, but the artifact does not show hidden execution, data access, persistence, or exfiltration.

Install only if you want a conservative instruction-layer firewall. Expect occasional overblocking, and do not treat the broad protection claims or optional raigo Cloud references as proof of a complete security boundary.

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: 92% confidence
• Finding: The skill description makes sweeping security claims and uses broad, generic activation language around 'comprehensive' protection for many attack classes. In agent ecosystems, overly broad descriptions can cause unintended invocation or over-trust, leading agents or users to rely on this skill in contexts it cannot actually enforce, especially since the file is only declarative text with no enforcement engine.

VirusTotal

65/65 vendors flagged this skill as clean.