Back to skill

Security audit

人生岔路模拟栈

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed personal life-choice reflection tool with optional, user-requested HTML export and no evidence of hidden persistence, exfiltration, or destructive behavior.

Install this if you want a reflective personal-decision report tool and are comfortable sharing only the life details you choose. Avoid giving identifiers, passwords, precise addresses, medical records, or third-party private records. Use HTML export only for a report you intentionally want saved, and check the output path before sharing or publishing it.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The skill is presented primarily as a conversational life-reflection assistant, but it also includes file-based report rendering and export behavior. That mismatch increases security risk because reviewers or runtime policy may underestimate the skill's actual capabilities, especially around reading Markdown inputs and writing HTML outputs that could expose sensitive personal data or be abused for unauthorized file generation.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill describes file-reading and HTML export behavior, but it does not declare an explicit tool scope such as permissions or allowed-tools. Even though the prose imposes some self-restrictions, those are not enforceable policy boundaries; in a permissive host, the agent could still read or write files beyond the intended workflow if prompt injection or model error occurs.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation without defining activation constraints or concrete trigger boundaries, so the agent may auto-select it for loosely related personal conversations. Because the skill is designed for reflective life-choice analysis, unintended invocation could steer sensitive user discussions, shape advice without explicit consent, or expose private context more broadly than the user expects.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This code explicitly defines the renderer as producing a 'Simplified Chinese HTML layout,' and later enforces lang="zh-CN" in the generated HTML. That is a natural-language locale policy concern because the skill forces a specific language/locale rather than offering a user-selectable option or documenting a justified regional constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This SVG contains user-facing natural-language content entirely in Chinese in the title and description, and additional visible labels throughout the image. Under the policy for all file types, forcing a specific language without opt-in can be a locale-policy violation when no choice or justification is provided.

Content

No source excerpt is available for this finding.