Security audit

命理大师

Security checks for vulnerabilities and agentic risk

Overview

This skill mixes astrology, finance, and university-application identities while requesting read, write, and command execution authority, so users should review it before installing.

Install only if you are comfortable with a poorly scoped skill that may be invoked for unrelated astrology, finance, or university-application tasks. Before use, the publisher should align the name, purpose, triggers, parameters, and output schema, and narrow or justify read/write/exec permissions with clear user controls.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Intent-Code Divergence

Medium

Confidence: 97% confidence
Finding: The manifest and description present materially conflicting identities: an astrology/fortune-telling skill, a finance tool, and a 'university-applications' processor, while also requesting read/exec/write capabilities. This mismatch can mislead users and agent orchestration into invoking the skill in unintended contexts, increasing the chance of inappropriate file access, command execution, or data handling under false pretenses.

Intent-Code Divergence

Medium

Confidence: 95% confidence
Finding: The documented activation examples refer to 'University Applications' workflows even though the skill is branded as '命理大师'. Contradictory trigger conditions can cause the agent to route unrelated user requests into a skill with read/write/exec privileges, creating confusion-driven misuse and possible unintended processing of sensitive data.

Intent-Code Divergence

Medium

Confidence: 96% confidence
Finding: The parameter and output schema describe 'university-applications' processing rather than fortune-telling behavior, indicating possible copy-paste contamination or repurposed instructions. In a skill with write and exec tools, this kind of semantic mismatch is dangerous because downstream systems or users may supply sensitive application content or trust outputs that do not correspond to the advertised function.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger condition 'use when 用户需要命理大师相关功能时使用' is overly broad and vague, providing no meaningful constraints on when the skill should activate. Broad triggers increase the risk of accidental or opportunistic invocation, especially for a skill declaring powerful capabilities like reading, writing, and executing commands.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill advertises file handling, external API integration, and command execution, but the surrounding documentation does not clearly explain the security consequences, permission boundaries, or data integrity risks of those actions. Users may authorize the skill underestimating its ability to modify files, send data externally, or run system commands, which can lead to data leakage or system impact.

Static analysis

No suspicious patterns detected.