Little Steve Agent Guard

Security checks across malware telemetry and agentic risk

Overview

This is a coherent local security wrapper, but it needs review because its approval and logging paths can undermine its own safety claims.

Install only if you want a broad local wrapper that can inspect and run other skills' scripts and keep local audit history. Avoid passing secrets in command arguments, periodically review or clear the reports directory, and treat the `confirm` command as sensitive because it can execute scripts without verifying a matching prior prompt.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (1)

Natural-Language Policy Violations

Medium

Confidence: 89% confidence
Finding: The skill requires a fixed confirmation phrase ("确认" or "confirm") rather than allowing the agent to obtain and interpret explicit user approval more flexibly. This can create brittle approval handling, increase the chance of accidental or coerced confirmations, and may encourage unsafe UX patterns where exact wording is treated as authorization.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal