Security audit

Newsletter Digest

Security checks across malware telemetry and agentic risk

Overview

This is a simple newsletter and article summarizing skill with no executable code, though users should avoid sending sensitive inbox content or private links.

Install only if you want an assistant to process newsletters, article links, reading lists, and preference signals. Do not forward confidential emails, proprietary newsletters, sensitive personal content, or links you are not authorized to share.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrases are broad enough to match ordinary user requests like article summaries or reading suggestions, which can cause the skill to activate when the user did not explicitly intend to invoke it. In a skill that processes forwarded newsletters and external links, accidental activation increases the chance of unintended content handling and surprise data exposure to the skill.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill encourages users to forward newsletters and submit article links but does not warn that this may involve processing third-party content, embedded tracking links, personal data, or subscription-only material. Without a clear warning, users may unknowingly share sensitive inbox content or cause the system to access untrusted URLs with insufficient awareness of privacy and security implications.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.