validation-agent

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a phased validation workflow with one overbroad trigger concern, but no evidence of hidden, destructive, or unrelated behavior.

Install if you want a phased validation helper. Be aware that broad phrases like phase 1 through phase 5 may cause it to activate more often than expected, so invoke it deliberately and review any validation commands before letting them run on sensitive or production repositories.

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: 96% confidence
Finding: The skill description is triggered by very broad phase-based language such as 'phase 1' through 'phase 5' rather than narrow, explicit conditions. This can cause the skill to be invoked in many unrelated contexts, increasing the chance that a high-privilege validation agent runs commands, scans repositories, or performs security checks when not actually intended.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal