Shaping & Breadboarding

Security checks across malware telemetry and agentic risk

Overview

This skill is a text-only product-planning aid for Shape Up methods and does not show harmful access, execution, or persistence behavior.

Install this if you want the agent to apply Shape Up-style shaping and breadboarding. Be aware it may steer general product-planning conversations toward that methodology, so disable or avoid it when you want neutral brainstorming or a different planning framework.

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: 95% confidence
Finding: The manifest description contains broad trigger phrases such as general product scoping and requirements discussions, which can cause the skill to activate in many ordinary conversations beyond a narrowly defined Shape Up workflow. Over-broad activation increases the chance of inappropriate routing, context hijacking, or unintentional influence over unrelated tasks, especially because the skill steers how problem framing and planning are performed.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal