Vajra

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Vajra API integration for analyzing content, with clear warnings that submitted content leaves your device and creates public/cached analysis results.

Install this only if you are comfortable using a Vajra API key and sending selected URLs or text to Vajra. Do not submit private, proprietary, or personally identifying material unless you accept that the analysis output may be cached server-side and exposed through a public permalink.

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: 90% confidence
Finding: The invocation text is very broad: it triggers on generic requests like 'analyze', 'evaluate', 'score', or 'assess' for arbitrary web content or text. In an agent environment, this can cause the skill to activate unexpectedly and send user-provided content to a third-party service, creating privacy and consent risks beyond the user's likely intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal