Back to skill

Security audit

书店

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only guidance skill with some confusing bookstore-versus-event wording, but it does not request system access, credentials, execution, persistence, or data mutation.

Before installing, understand that this skill may answer bookstore requests with event or exhibition-style fields such as tickets, entry rules, and venue logistics. It appears safe from a security standpoint, but the publisher should clarify whether it is for bookstores, exhibitions, or ticketed attractions.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The manifest description says the skill provides bookstore recommendation lists and travel guidance, while the rest of the document specifies event/exhibition ticketing and venue operations. This inconsistency undermines trust boundaries for tool selection and can cause the agent to expose users to unintended capabilities or irrelevant transactional guidance when they only requested bookstore information.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill is presented as a bookstore recommendation tool, but its documented filters and outputs describe ticketed events, exhibitions, seating, entry rules, and performance logistics. This semantic mismatch can cause the agent to invoke the skill in contexts unrelated to its actual behavior, leading to user deception, incorrect routing, or unauthorized handling of event-booking workflows under a misleading identity.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The activation description is broad enough that the skill may be invoked whenever users search for bookstores or plan related travel, despite the body describing a different domain. Overbroad invocation increases the chance of inappropriate tool use, misrouting, and confusing or unsafe outputs because the skill may be selected outside its true competence.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The skill name, description, and examples are entirely in Chinese, and the file does not indicate that language choice is optional or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.