ClawHub
Back to skill

Security audit

pptx

Security checks for vulnerabilities and agentic risk

Overview

This PowerPoint skill is purpose-aligned and does not show hidden, persistent, destructive, or credential-seeking behavior.

Install for PowerPoint-specific work. Be aware that it may activate for broad presentation-design requests, and some referenced helper files are not present in this package, so local commands should only be run against presentation files you intend to process.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill metadata description is broad enough to activate on generic mentions of slides, PPT, or presentations, which can cause over-selection of this skill outside clearly scoped file-editing or analysis tasks. In an agentic system, overly broad routing increases the chance that filesystem or command-capable tooling is invoked unnecessarily on untrusted user requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The 'When to Use This Skill' section uses permissive trigger language like 'mentions slides, PPT, or presentations,' which lacks constraints and can cause the skill to run on loosely related conversations. Because this skill includes operational guidance for local file processing and script execution, accidental invocation expands the attack surface and may lead the agent to take unnecessary actions on user-supplied files.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.