Back to skill

Security audit

Pptx Generation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language PowerPoint generation guide that creates .pptx files, with no hidden execution, credential access, network retrieval, or persistence beyond the expected output file.

Install this if you want Chinese-language guidance for generating PowerPoint files. Before use, choose the output path deliberately and avoid overwriting existing files; provide your preferred language or font requirements if Chinese defaults are not appropriate.

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 (10)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description lists trigger phrases such as "制作PPT" and "创建pptx", which are broad natural-language requests that could overlap with ordinary conversation and cause unintended invocation. The file does not provide exclusion conditions, scope constraints, or negative examples to clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
72% confidence
Finding

The natural-language instructions and description are entirely in Chinese and do not indicate that the user may choose another language or locale. This can constitute a language-policy violation when a skill implicitly constrains interaction language without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file presents all user-facing instructions and usage guidance exclusively in Chinese. Under the policy, forcing a specific language without user opt-in or documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown exemplar presents all instructions, labels, and examples exclusively in Chinese, which can amount to a language/locale policy violation when no user opt-in or documented regional limitation is provided. The file does not indicate that the skill is China-specific or that users may choose another language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The file is entirely written as a Chinese output template and presents the expected report headings and content in Chinese without any indication that language is optional or region-specific. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The entire skill reference is written only in Chinese and prescribes Chinese-specific typography choices such as 黑体、宋体、楷体, with no indication that the skill is China-specific or that users may opt into another language or locale. This can violate language/locale policy because it implicitly forces a specific locale rather than offering a choice or documenting a justified regional constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file hard-codes Chinese font families such as 黑体, 宋体, and 楷体 as required defaults. That creates a locale-specific constraint in natural-language guidance without opt-in, which matches the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill repeatedly instructs that output should be saved as a .pptx file, but does not clearly surface this as a user-facing warning or require confirmation before writing to disk. In an agent environment, silent file creation can lead to unexpected persistence of sensitive or misleading content and may surprise users about where data is stored.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains only Chinese instructions and examples, which can amount to an implicit language constraint if the skill is expected for a general audience. The file does not mention that Chinese output is optional, selectable, or limited to a China-specific use case.

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 instructs determining a save path and writing a .pptx file, but it provides no safety requirements around path restriction, overwrite protection, or explicit user confirmation. In an agent context, this can lead to unintended file creation or destructive overwrites of existing user files, especially if the model infers paths automatically or honors untrusted path input.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.