Dromo

Security checks across malware telemetry and agentic risk

Overview

This Dromo integration appears legitimate, but it gives an authenticated agent broad power over business import data without enough guardrails for deletes, downloads, and raw API requests.

Install only if you intend to let an agent operate through your Dromo account via Membrane. Use a least-privileged account where possible, review action IDs and inputs before execution, require explicit approval before create/update/delete or proxy requests, and treat presigned download URLs as sensitive.

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: 90% confidence
Finding: The skill documents several destructive operations such as deleting uploads, headless imports, and import schemas, but it provides no warning, confirmation, or approval guidance before invoking them. In an agent setting, this increases the risk of accidental or overly broad data deletion because the model may treat these actions as routine without recognizing their irreversible impact.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal