Back to skill

Security audit

PPT自动生成

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward PPT-generation workflow using disclosed third-party web services, with expected local file output and no hidden code or persistence.

Before using this skill, expect to log in to Tongyi Qianwen or Kimi and to share your PPT topic or outline with that provider. Ask the agent to confirm the download location and filename before saving the generated PPT, especially on a shared machine.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

All user-facing instructions and labels in the skill are presented only in Chinese, with no indication that users may choose another language or that the skill is region-specific. This can violate language/locale policy when a skill effectively forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly states that generated PPT files will be saved locally, but it does not require prior user consent, clarify the destination path before writing, or describe any safeguards around overwriting or sensitive storage locations. This can lead to unexpected local file creation and privacy or usability issues, especially when the agent operates on a user's machine or in a shared environment.

Content

No source excerpt is available for this finding.