Security audit

Pudding Data Story

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent data-storytelling guide with a local audit helper, and I did not find hidden credential access, persistence, exfiltration, or destructive behavior.

Installers should understand that this skill may be invoked for a wide range of visualization and data-story requests. Review whether that routing behavior is desirable, and run the included audit script only against project folders you intend the agent to inspect.

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: 78% confidence
Finding: The trigger description is broad enough to match many generic visualization, scrollytelling, audit, and 'not like a normal chart' requests, which can cause the skill to activate outside its intended niche. Unintended invocation can steer unrelated tasks into this skill's workflow, causing prompt hijacking of the user experience, unnecessary file reads, and inappropriate instructions being applied to the wrong project.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill enables implicit invocation while advertising a very broad, natural-language use case with no explicit trigger constraints. This can cause the agent to activate in unintended contexts, leading to overbroad routing, unexpected handling of user data, or use of the skill when a safer or more appropriate skill should have been selected.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.