autoglmasr

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent cloud audio transcription MCP guide, but users should understand that selected audio is sent to Zhipu/BigModel for processing.

Install only if you are comfortable sending chosen audio files to Zhipu/BigModel for transcription. Use a dedicated API key, check the npm package and GitHub source before running npx, pin a known version where possible, and avoid submitting sensitive or regulated recordings without approval.

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: 94% confidence
Finding: The skill sends user-provided audio to an external ASR provider, but the description and usage guidance do not clearly warn users that audio content leaves the local environment and is uploaded to a third-party service. This can cause unintended disclosure of sensitive conversations, personal data, or regulated information when agents or users assume transcription happens locally.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal