Security audit

Iambic Pentameter

Security checks across malware telemetry and agentic risk

Overview

This skill only changes the agent’s writing style into iambic pentameter and does not request access to files, credentials, tools, or external services.

Install this only if you want responses styled as Shakespeare-like metered verse. Avoid using it for precision-heavy work such as legal, medical, coding, JSON, or procedural tasks where plain language and exact formatting are more important than style.

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 (2)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger description is broad enough to match common requests such as 'write it fancy' or 'speak like Shakespeare', which can cause the skill to activate when the user did not clearly request metered verse. Unintended invocation can degrade response quality, interfere with normal task handling, and cause formatting changes that are inappropriate for mixed-purpose or instruction-heavy prompts.

Natural-Language Policy Violations

Medium

Confidence: 85% confidence
Finding: The skill instructs the agent to write as much output as possible in iambic pentameter across many request types, which imposes a stylistic transformation without requiring explicit user consent at runtime. This can distort clarity, omit precision, or make practical answers less usable, especially for factual or procedural requests where form should remain subordinate to user intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.