Security audit

Prompt Injection Removal

Security checks across malware telemetry and agentic risk

Overview

This appears to be a defensive prompt-injection cleanup skill, and the flagged injection phrases are part of its stated safety purpose.

Install only if you want a skill that helps an agent treat user-provided or retrieved text as untrusted input. Its prompt-injection examples may look alarming in isolation, but the supplied evidence indicates they are used defensively; still review the installed files if you need full assurance because the local workspace did not include a separate raw bundle for deeper verification.

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

66/66 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: PROMPT.md:15

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: references/security.md:19

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: SKILL.md:31