Zonka Feedback

Security checks across malware telemetry and agentic risk

Overview

This looks like a real Zonka Feedback integration, but it gives an agent broad authenticated ability to change or delete business feedback data without enough built-in guardrails.

Install only if you are comfortable letting an agent act through your Membrane connection in Zonka Feedback. Use a least-privileged account, verify the npm CLI source/version, and require explicit confirmation before any create, update, workflow automation, raw proxy, or delete operation.

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: 79% confidence
Finding: The invocation description is broad enough that an agent may select this skill for many generic requests involving feedback, records, or workflows without sufficient user intent validation. Over-broad routing can cause unnecessary external access, data exposure, or unintended actions in the user's Zonka Feedback environment if the skill is invoked in the wrong context.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal