Back to skill

Security audit

PPT Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently generates HTML slide decks from user-provided content and references, with no bundled executable code or hidden persistence.

Before installing, users should be comfortable sharing any uploaded reference images or files for processing, and should expect the generated HTML presentation to be saved locally and returned as a file. Avoid uploading confidential material unless the surrounding platform and tools are approved for that data.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description and operating instructions are entirely in Chinese and implicitly steer the interaction and output toward a single language/locale. There is no opt-in language choice or explicit justification that this is a China-specific or Chinese-only skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly states it will call a tool to download user-uploaded images, which is a data-handling operation involving user-provided files. The markdown does not disclose any caution about accessing, downloading, or processing uploaded content, even though the skill description is the primary user-facing warning surface here.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill description includes creating a local file and transmitting it back to the user, which affects user data and system state. The markdown does not include any explicit notice that the skill will write a local HTML file and send that artifact onward.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.