SocialRails

Security checks across malware telemetry and agentic risk

Overview

This is a coherent SocialRails integration that uses a configured API key to manage social posts, with real account-impacting capabilities users should handle carefully.

Install only if you trust SocialRails and want your agent to access connected social media accounts. Prefer least-privilege API scopes, review generated or scheduled content before write actions, and keep the API base URL set to the intended SocialRails endpoint.

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 (2)

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The README presents scheduling and account-management capabilities as routine commands but does not clearly warn that using the skill can queue or publish content to the user's connected social accounts. This can cause users to invoke the skill without understanding the real-world effect of the action, increasing the risk of unintended posts, reputational harm, or misuse if the chat prompt is ambiguous or manipulated.

Missing User Warnings

Low

Confidence: 86% confidence
Finding: The manifest explicitly offers commands to list connected social media accounts and view analytics, but it does not warn users that potentially sensitive account metadata and performance data may be retrieved and displayed in chat. In a chat-integrated skill, this can lead to unintended disclosure to other viewers of the conversation, logs, or downstream systems that retain chat content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal