Donor Message

Security checks across malware telemetry and agentic risk

Overview

This is a simple donor-message drafting skill with no code, credentials, background behavior, or external access.

Safe to install as a drafting aid. Users should avoid providing unnecessary donor personal data, payment details, or confidential fundraising records unless needed for the specific message they ask the agent to draft.

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
87% confidence
Finding
The skill's usage triggers are broad enough to match generic writing-assistance requests rather than a narrowly scoped donor-communication task. That can cause inappropriate activation in unrelated contexts, exposing user content to the skill and producing fundraising-oriented messaging where it was not intended, though the skill itself does not contain more dangerous behaviors such as exfiltration or instruction hijacking.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal