ClawHub
Back to skill

Security audit

my skill

Security checks for vulnerabilities and agentic risk

Overview

This is a simple presentation-writing skill with no code, persistence, credential use, or hidden system behavior.

Installers should understand that this skill may activate for many slide-related requests, but the reviewed artifact is only presentation guidance and does not add code execution, data access, or persistent behavior.

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
91% confidence
Finding

The skill metadata uses broad trigger language like 'create, design, or generate a PowerPoint presentation,' which can match a wide range of common user requests without defining exclusion criteria or activation boundaries. In an agent environment, this can cause over-invocation or routing conflicts, leading the skill to handle requests outside its intended scope and increasing the chance of unintended actions or prompt-surface expansion.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The 'When to Use' section ends with a catch-all rule for 'Any request involving PowerPoint, slides, or presentation creation,' which is overly permissive and can cause the skill to activate on ambiguous or marginally related requests. This broad scope increases the risk of unintended delegation, tool misuse, or interference with more specialized skills that should handle adjacent tasks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.