Back to skill

Security audit

Promotional Generation

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language promotional-material generator that saves user-requested output files and shows no hidden code, network access, credential use, or persistence beyond generated files.

Install this if you want a Chinese-language workflow for creating promotional materials. When using it, tell the agent where to save files and ask before overwriting existing work; consider tightening activation phrases if accidental invocation would be disruptive.

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 (8)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description lists trigger phrases such as “宣传单”, “宣传册”, and “宣传海报”, which are generic content nouns rather than clear invocation commands. These common terms could appear in ordinary user requests or discussions and may cause the skill to activate unintentionally because the scope and exclusions are not defined.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill explicitly instructs the agent to save generated content as files and later report file locations, but it provides no safety constraints around where files may be written, whether user confirmation is required, or what content is permissible to persist. In an agent environment with filesystem access, this can lead to unintended file creation, overwriting user data, or persistence of unsafe/generated content without clear consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all instructions and usage guidance exclusively in Chinese, and nowhere indicates that users may choose another language or that the skill is intended only for a Chinese-language context. Under the policy rule, 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
86% confidence
Finding

This markdown template is entirely written as a prescriptive exemplar in Chinese and provides output examples only in Chinese, with no indication that users may choose another language. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

This markdown file is entirely written as a Chinese-only template and provides no indication that the user may choose another language or locale. Under the policy rule for natural-language violations, a skill that effectively requires a specific language without opt-in can be non-compliant unless the locale restriction is explicitly justified.

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 file presents all task goals, steps, and examples only in Chinese. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale policy issue when no alternative language option or justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The document specifies fixed Chinese fonts such as 黑体 and 宋体 for headings and body text, which imposes a specific language/locale presentation standard. Because the file does not offer any user opt-in, alternative locale handling, or justification that the skill is region-specific, this is a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file includes an output step, '文件输出 | 保存为相应格式文件', which indicates user data will be written to files. The description does not provide any warning or note about where files are saved, whether existing files may be overwritten, or any user-data implications.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.