baiyin-image-generate-skill

Security checks across malware telemetry and agentic risk

Overview

The skill may be useful, but it appears to let an agent upload local files to a remote service without clear user confirmation.

Review before installing. Only use this skill with files you intentionally want to send to its remote service, and prefer a version that asks for explicit confirmation and names the destination before uploading any local path.

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
96% confidence
Finding
The skill instructs the agent to treat any non-HTTP(S) input as a local path and automatically upload it to a remote endpoint, without requiring explicit user confirmation or warning that data will leave the local environment. This creates a real risk of unintended exfiltration of local files, sensitive attachments, or private resources if a user supplies a path, pasted tokenized reference, or other non-public locator.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal