Back to skill

Security audit

Canyin Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language restaurant operations guide with no executable code, hidden installation behavior, persistence, or sensitive data access.

Install this if you want Chinese-language small restaurant operations templates. Review and adapt any marketing or review-incentive scripts to local law and delivery-platform rules before using them with real customers.

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
  • 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
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger terms are broad and generic for the restaurant domain, so the skill may activate for ordinary food-business discussions that did not intend to invoke this workflow. This is not a code-execution or data-theft issue, but it can cause unintended routing, irrelevant responses, and possible overshadowing of more appropriate skills in multi-skill environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The entire skill reference is written as fixed Chinese-language scripts and templates, with no indication that the user can choose another language or locale. Under the stated policy, natural-language content that effectively enforces a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing natural-language content in the skill file is Chinese, and the skill does not state that it supports other languages or that Chinese is an intentional region-specific constraint. Under the language/locale policy, forcing a single language without user opt-in can be a policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

Line L191 includes the phrase "全国通用" for menu items, which presents a broad locale assumption in natural language. This can conflict with language/locale policy expectations because it implies one default regional fit rather than offering a locale-specific choice or clearly scoping the advice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.