WeChat to Obsidian

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed WeChat-to-Obsidian clipping helper that uses browser automation and local file writes for its stated purpose.

Install only if you are comfortable adding agent-browser and allowing the agent to open WeChat article pages, run page-extraction JavaScript, download article images, and write Markdown plus attachments to a path you provide or confirm.

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: 90% confidence
Finding: The trigger list includes very generic phrases like “剪藏”, “帮我存”, and “保存到这个路径”, which can cause the skill to activate in conversations where the user did not clearly intend to process a WeChat article. In an agent setting, overly broad activation increases the chance of unintended browsing, content extraction, or local file-writing behavior being invoked from ambiguous prompts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal