Soci

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate Soci integration, but it gives an agent broad authenticated power to change or delete Soci data without clear confirmation safeguards.

Install only if you trust Membrane and are comfortable connecting a Soci account. Use the least-privileged account available, revoke the connection when finished, and require the agent to show the exact action or endpoint, HTTP method, data being changed, and expected effect before creating, editing, publishing, scheduling, or deleting anything.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The skill description is broad enough to match generic requests about managing data or automating workflows, which could cause the agent to invoke this skill outside a clearly intended Soci context. Over-broad routing increases the chance of unintended external-system access or actions being proposed when the user did not explicitly ask to operate on Soci.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The documentation explicitly enables direct proxy requests with mutating HTTP methods like POST, PUT, PATCH, and DELETE, but does not warn that these can change or delete real Soci data. In an agent setting, this omission can lead to unsafe execution of destructive operations without confirmation, scoping, or dry-run safeguards.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal