Security audit

Reef Prompt Guard

Security checks across malware telemetry and agentic risk

Overview

This is a legitimate local prompt-injection filter, but one documented API integration pattern could expose a server to command injection if copied with untrusted input.

The Python filter itself appears purpose-aligned for local scanning. Before installing or adopting it, avoid copying the documented execSync shell-string API example for untrusted input; use a direct Python import, stdin, or a safe child-process argument array instead.

SkillSpector

By NVIDIA

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: references/attack-patterns.md:27

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: SKILL.md:14