Story Narrative

Security checks across malware telemetry and agentic risk

Overview

This is a narrative-writing methodology skill with only Markdown instructions and no executable, credential, network, persistence, or destructive behavior.

Install this if you want structured help turning ideas into narratives and solution reports. Be aware that its trigger terms are broad, so it may be invoked in more writing or planning contexts than expected; disable or avoid it for tasks where you do not want narrative framing.

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: 91% confidence
Finding: The trigger list contains broad phrases such as '故事叙述', '英雄旅程', and especially 'meta-skill-system' without scope boundaries, exclusions, or disambiguation guidance. This can cause unintended activation in unrelated contexts, leading the agent to apply the skill when the user did not explicitly request it, which may distort outputs or override more appropriate behaviors.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal