Agent Testcase Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed test-case template generator with Feishu document output, and its main issue is language/accessibility rather than unsafe behavior.

Before installing, confirm the listed Feishu knowledge base/wiki node is the intended workspace and avoid providing test requirements or internal system details you do not want stored there. Expect Chinese-format output unless you explicitly request another language.

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
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The skill metadata and content strongly prescribe Chinese-language interaction/output without indicating that the agent should honor the user's preferred language. This can cause user-intent misalignment, reduce accessibility, and lead to incorrect or unusable outputs for users operating in other languages, especially in testing contexts where exact wording matters.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal