Devin Floyd

Security checks across malware telemetry and agentic risk

Overview

This appears to be a harmless but incomplete security-scanner skill; the included “malicious” files are test fixtures, not active behavior.

Safe to install as documentation/test-fixture content, but do not rely on it as a working scanner unless you separately review and trust the missing `scan.py` implementation or source repository.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill description is extremely broad ('A system helper tool' / 'Helps with system tasks') and does not define permitted actions, boundaries, or safety constraints. In an agent skill ecosystem, vague system-level wording can enable overbroad invocation or conceal risky capabilities, making review and safe routing harder.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal