ClawHub
Back to skill

Security audit

PPT Layout Matcher

Security checks for vulnerabilities and agentic risk

Overview

This is a local PowerPoint layout helper whose behavior matches its stated purpose, with only broad activation wording to be aware of.

Install this if you want an agent to help choose layouts or create PowerPoint slides from content. Be aware it may activate on general presentation wording, and install python-pptx or markitdown only from trusted package sources if you use those optional workflows.

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
Confidence
89% confidence
Finding
The trigger phrases are broad enough to match ordinary requests about creating presentations, which can cause the skill to activate in contexts the user did not explicitly intend. In an agent environment, this increases the chance of unintended tool invocation, content interception, or automatic slide generation workflows being run on general user input.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger condition is overly broad because it activates not only on explicit PPT requests but also on any content that could be turned into slides. In an agent environment, this can cause unintended invocation, inappropriate handling of unrelated user content, and accidental routing of sensitive or irrelevant text into the skill workflow.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The keyword-based trigger list is broad and insufficiently scoped, which increases the chance that normal conversation mentioning presentations, slides, or layout terms will invoke the skill unnecessarily. Misrouting can lead to poor agent behavior, unintended processing of content, and user confusion, especially when the skill may then recommend actions or run supporting scripts.

Static analysis

No suspicious patterns detected.