Ada Lovelace · 诗性科学视角

Security checks across malware telemetry and agentic risk

Overview

This is a single markdown style/persona skill with no code or data access, though its broad triggers may activate the Ada Lovelace-style voice unexpectedly.

Install this if you want a Chinese-language Ada Lovelace-inspired creative reasoning style. Be aware it may activate on broad conceptual prompts, and verify historical quotes or factual claims when accuracy matters.

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: 93% confidence
Finding: The trigger phrases are broad, generic, and semantically common in ordinary discussion, which can cause the skill to activate unintentionally outside the author's intended context. This increases the chance of prompt-routing mistakes, persona hijacking of unrelated tasks, and unpredictable behavior when users discuss abstract topics like principles, foresight, or possibility space.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal