Security audit

cn-holiday

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese holiday lookup tool that sends date queries to a disclosed public API.

Install this if you are comfortable with holiday queries being sent to timor.tech. The skill does not need an API key and does not show signs of persistence or local data access.

A.I.G

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.
md
2. Run `bun scripts/holiday.ts --help` in this skill directory.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 89% confidence
Finding: The skill invokes a network-backed script and external API, but the manifest does not declare any tool scope or allowed-tools boundaries. This creates a least-privilege and transparency problem: the runtime may permit broader capabilities than users or reviewers expect, and external requests can expose queried dates or user-derived inputs to a third party.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill advertises trigger words such as "上班", "放假", and a catch-all pattern of any "[日期] 是否放假/上班" input. These phrases are broad everyday expressions and the file does not provide exclusion conditions or narrower context, which could cause unintended invocation outside a clearly bounded holiday-query context.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: This code constructs a URL with caller-supplied query parameters and sends it over the network via fetch, which can transmit user or system data to an external service. In this file there is no confirmation prompt, print/log statement, or comment/docstring disclosing that outbound network transmission occurs.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.