Back to skill

Security audit

wine & food

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped Sippai restaurant wine-and-food lookup skill that uses a disclosed MCP endpoint and does not show hidden execution, persistence, or data theft behavior.

Install only if you intend to let the agent query Sippai's MCP service for restaurant, wine, and dish data. If your host requires an API key, provide it through normal secure environment or host configuration rather than placing secrets in the skill files.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description is explicitly split into Chinese and English and presents the skill in those two languages only, with no indication that the user may choose another language or that output follows the user's preferred locale. Under the stated policy, constraining language/locale without user opt-in is a natural-language policy violation unless clearly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language fields such as name, description, usage conditions, workflow notes, tool summaries, and environment guidance are presented exclusively in Chinese. Because the file does not state that the skill is intended only for Chinese-speaking users or offer any language choice, it effectively enforces a specific language without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README includes a natural-language requirement that descriptions be '中英可读' (readable in Chinese and English). This imposes a specific language policy rather than presenting language use as optional or user-selected, which matches the locale/language policy concern in SQP-3.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.