ClawHub
Back to skill

Security audit

Blockly Block Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Blockly helper skill with broad trigger wording, but no hidden code, persistence, credential access, or destructive behavior.

Install this if you want a reusable assistant workflow for the specific Blockly enable/disable block feature request. Be aware it may be invoked for unrelated prompts because its trigger keywords are too generic, so review or narrow the trigger metadata if your environment uses automatic skill selection.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description is broad enough to match generic requests such as general-help, enhancement, or implementation support, which can cause the skill to be invoked outside its narrowly intended Blockly feature-request context. Over-broad routing increases the chance of misapplication, unintended context capture, and unsafe or low-quality task handling when a more appropriate skill should have been selected.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The keyword list includes highly generic terms such as add, block, enable, disable, request, and enhancement, which are common across many unrelated user prompts. This can lead to unintended invocation and routing collisions, especially in multi-skill environments, causing irrelevant guidance, context confusion, or accidental handling of requests by the wrong skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises very broad invocation criteria such as general help, enhancement, feature request, practical workflow, artifact, checklist, analysis, or implementation support, which greatly expands when the agent may select it. Overbroad routing increases the chance this skill is invoked in unrelated contexts, causing unintended prompt influence, data exposure to an unnecessary skill, or unsafe task execution beyond its narrowly described Blockly use case.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.