xfire Security PR Review

• Outcome: Pass
• Latest audit: May 28, 2026, 11:43 AM
• Version:
  0.1.2

Overview

This skill is a disclosed security-review wrapper that sends selected code context to external AI providers, with credential and privacy risks users should manage before use.

Install only if you are allowed to share the target code or diff with the selected AI providers. Use the minimum needed provider keys and least-privilege GitHub token, avoid debug output on sensitive repositories unless necessary, and review cache/auth/output files for sensitive content after use.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill explicitly states it sends code to three external AI agents, but it does not present a prominent privacy/security warning about transmitting potentially sensitive source code, diffs, secrets, or proprietary data to third-party services. In a security-review skill, users may reasonably assume safer handling, so the missing disclosure increases the risk of unintended data exfiltration to external providers.

VirusTotal

64/64 vendors flagged this skill as clean.