Cnvrgio

Security checks across malware telemetry and agentic risk

Overview

This Cnvrg.io skill is a disclosed integration, but it gives an agent broad authenticated API control, including write and delete capability, without clear safety limits.

Install only if you trust Membrane with access to the intended Cnvrg.io account and are comfortable with the agent potentially performing broad API operations. Use a least-privileged Cnvrg.io account or connection, consider pinning the CLI version, and require explicit approval before any write, delete, secret, deployment, endpoint, cluster, or organization-level operation.

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: 92% confidence
Finding: The skill explicitly documents both action execution and raw proxy requests against the Cnvrg.io API, including methods like POST, PUT, PATCH, and DELETE, but does not warn that these operations can change or destroy remote resources. In an agent setting, lack of explicit confirmation guidance increases the chance of accidental destructive actions against live datasets, deployments, secrets, or workflows.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal