Edvisage Social Kit

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only social posting skill, but it includes under-scoped public posting guidance and anti-detection framing that users should review before installing.

Install only if you will use it for drafting or explicitly approved posts. Do not use the anti-detection or stealth-automation guidance, and confirm each target platform permits the workflow before allowing an agent to post, reply, or monitor engagement.

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: 93% confidence
Finding: This markdown file describes broad social-posting capabilities but does not define explicit trigger phrases, boundaries, or negative examples. Without clear activation constraints, an agent may invoke the skill during ordinary conversation about social media or online presence.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal