Back to skill

Security audit

Presentation Maker

Security checks for vulnerabilities and agentic risk

Overview

This is a simple presentation-generation skill with no bundled code, credential use, persistence, or hidden high-impact behavior.

This appears safe to install from a security perspective. Before relying on it, note that the package is minimal and may only provide prompt guidance rather than working export functionality, since no implementation files are included.

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
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

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The package description "AI presentation generator" is overly broad and does not clearly bound when the skill should be selected. In agentic systems, vague metadata can cause over-invocation or invocation in unintended contexts, increasing the chance that the skill is used on inappropriate inputs or gains access to workflows it was not meant to handle.

Content

No source excerpt is available for this finding.