Blockly Block Builder

• Outcome: Pass
• Latest audit: Jun 14, 2026 at 7:22 AM UTC
• Version:
  0.1.1

Overview

This text-only Blockly helper is clean and purpose-aligned, but its broad auto-invocation wording may make it trigger more often than intended.

Install this if you want a lightweight helper for the Blockly enable/disable block feature request. Be aware it may activate on broad terms like add, block, enable, or disable, so explicit invocation with $blockly-block-builder is preferable when you want this skill, and you may want the publisher to narrow the triggers in a future version.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The skill description is written broadly enough to match generic help and implementation requests, which can cause the skill to activate outside the narrow Blockly feature-request scenario. Misrouting is dangerous because an unintended skill may shape the agent's response, suppress more relevant skills, or provide irrelevant implementation guidance in contexts where the user did not request Blockly-specific help.

Vague Triggers

Medium

• Confidence: 98% confidence
• Finding: The trigger list includes very generic tokens such as 'add', 'block', 'enable', and 'disable', which are likely to appear in many unrelated conversations. This increases the chance of accidental invocation and prompt-routing errors, making the agent less predictable and potentially exposing users to incorrect workflows or code guidance unrelated to their actual task.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: Enabling implicit invocation without narrowly defined trigger constraints can cause the skill to activate on ordinary user requests that merely resemble the intended use case. In this skill, the broad enhancement/help context increases the chance of unintended routing, which may expose users to unreviewed behavior, unexpected prompt injection surface, or incorrect task handling.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The default prompt is phrased as a broad natural-language help request and includes generic terms like 'help' and feature-request language that can overlap with normal user conversations. That overlap makes accidental invocation more likely, especially when combined with implicit invocation, causing this skill to intercept requests outside its narrow intended scope.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger scope is broad and uses generic phrases like 'general-help' and 'practical workflow' with minimal exclusion conditions, which can cause the skill to activate for loosely related requests. In an agent system, overbroad activation can route unrelated user prompts into this skill, leading to incorrect handling, prompt overshadowing, or unintended disclosure of contextual instructions and artifacts.

VirusTotal

61/61 vendors flagged this skill as clean.