Qa Expert Review

Security checks across malware telemetry and agentic risk

Overview

This appears to be a low-impact test-case review skill with one routing-scope caution, not evidence of unsafe behavior.

Install this if you want help reviewing or correcting test cases. Be aware it may activate for broad quality-review wording, so give clear test-case context and avoid passing unrelated sensitive material into review prompts.

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
89% confidence
Finding
The activation condition is overly broad because it triggers not only on specific phrases but also on the generic need for 'quality control' of AI output. In a multi-skill agent, this can cause the skill to activate in many unrelated review contexts, leading to inappropriate interception of tasks, unnecessary access to sensitive test artifacts, and confused delegation behavior.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal