ClawHub
Back to skill

Security audit

discussion-vocabulary-diagnosis

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable academic writing diagnosis skill with a minor risk of activating on broad vocabulary-help requests.

Install this if you want focused feedback on academic vocabulary in psychology Discussion sections. Be aware that generic trigger phrases like "check vocabulary" may invoke this skill for broader writing-help requests, but the inspected artifact does not contain code execution, data access, persistence, or credential handling.

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 (1)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger list includes generic phrases such as "check vocabulary" and "academic expressions" that can plausibly appear in many unrelated user requests. This can cause the skill to activate outside its intended narrow context, leading to prompt/skill hijacking of ordinary conversations and unintended application of its constrained diagnostic behavior.

Static analysis

No suspicious patterns detected.