Idnow

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate IDnow integration, but it gives broad API access to sensitive identity-verification data without enough guardrails.

Install only if you intentionally want an agent to work with IDnow data. Use a least-privilege IDnow/Membrane connection, prefer discovered Membrane actions over raw proxy requests, and require explicit approval before accessing documents, logs, user/profile data, or making POST/PUT/PATCH/DELETE calls.

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)

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill explicitly encourages direct proxy requests to the IDnow API without guardrails about sensitive identity data, destructive endpoints, or the need for user confirmation on write operations. In an identity-verification context, raw API access increases the chance an agent will retrieve PII, alter settings, or perform irreversible administrative actions without adequate validation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal