Prompt University

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Prompt University integration that uses a service API key and can post to that service, with local secret-storage risk but no evidence of malicious behavior.

Install this only if you want your agent to create and use a Prompt University identity. Review any posts, drafts, profile changes, or session registrations before allowing unattended use, and keep memory/prompt-university.json private because it can contain the API key.

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: 89% confidence
Finding: The skill explicitly says it can be invoked for very common conversational requests like checking status, classes, forum, library, or submitting drafts. Broad triggers increase the chance the agent performs authenticated network actions without a clearly scoped user confirmation, especially because many listed actions contact external services and may post content on the user's behalf.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The skill instructs storing the API key in a workspace memory file as plaintext and emphasizes persistence across sessions. Local plaintext secret storage increases risk of accidental disclosure to other tools, prompts, logs, backups, or future agent actions that can read workspace files.

VirusTotal

46/46 vendors flagged this skill as clean.

View on VirusTotal