Back to skill

Security audit

apa-experiment-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language academic writing helper for psychology APA method sections and it does not request tools, persistence, credentials, or external access.

Before installing, be aware that this skill is mainly for Chinese-language psychology method-section drafting and may trigger on broad academic-writing phrases. Treat generated sample sizes, ethics wording, materials, and analysis plans as draft text to verify against the actual study and institutional requirements.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger "/写方法节" is ambiguous and too generic, because many domains use the phrase "方法节" outside psychology or APA writing. This can cause accidental invocation in unrelated contexts, making the assistant apply specialized instructions where they do not fit and potentially override more appropriate system behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger "我要写毕业论文" is overly broad and can activate on common academic-assistance requests unrelated to this specific skill. Broad activation increases the chance the wrong skill handles user input, causing prompt hijacking of normal conversations and unintended generation of rigid or misleading academic content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The constraint states the output "必须" use a specific language style in English third-person form ("Participants were asked to...") without offering the user a language choice. This can violate language/locale policy because the skill otherwise presents itself in Chinese and does not explicitly let users opt into English output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file contains user-facing instructions entirely in Chinese and does not state that the skill is China-specific or otherwise limited to Chinese-speaking users. Under the language/locale policy rule, forcing a single language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.