Baidu Yijian Vision

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Baidu vision-API helper that sends user-selected images and ROI metadata for analysis, with no evidence of hidden or unrelated behavior.

Install only if you are comfortable sending the selected images, ROI/tripwire coordinates, prompts, and related metadata to Baidu Yijian using your API key. Avoid using it on confidential, regulated, or surveillance images unless your organization has approved that data flow.

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: 89% confidence
Finding: The workflow instructs users to invoke the skill with an image and custom ROI payload sent to an external endpoint (`ep-xxxx-yyyy`), but it does not explicitly disclose that the image and associated metadata leave the local environment. In a vision-analysis skill, images may contain sensitive operational, personal, or security-monitoring data, so omission of this disclosure can cause unintended data exfiltration and misuse in privacy-sensitive contexts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal