ClawHub
Back to skill

Security audit

中国日历

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese holiday calendar helper that uses a disclosed third-party API and does not install code, persist itself, or request sensitive local access.

Install this if you are comfortable with calendar date lookups being sent to timor.tech. Avoid using it for confidential planning workflows unless third-party outbound API use is allowed in your environment.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (5)

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill description and instructions are predominantly in Chinese and present the skill as Chinese-language by default, but they do not state that language is optional or user-selectable. Under the policy, forcing a specific language without opt-in can be a natural-language locale violation unless the constraint is explicitly justified.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# 查询今天
curl -s "https://timor.tech/api/holiday/info/$(date +%Y-%m-%d)"

# 查询指定日期
curl -s "https://timor.tech/api/holiday/info/2026-02-28"
Confidence
94% confidence
Finding
This command sends date queries to an external service, creating a data egress path from the agent environment to timor.tech. Even though the payload is simple, external transmission can leak behavioral patterns, schedule-related context, and network metadata, and it introduces dependency on an untrusted third-party service.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# 查询2026年所有节假日
curl -s "https://timor.tech/api/holiday/year/2026/"
```

### 批量查询多个日期
Confidence
94% confidence
Finding
The yearly holiday lookup also performs outbound requests to a third-party API, exposing usage metadata and establishing a trust dependency on remote content. Bulk queries may reveal organizational planning patterns and can fail or be manipulated if the service becomes unavailable or returns incorrect data.

External Transmission

Medium
Category
Data Exfiltration
Content
### 判断明天是否需要上班

```bash
response=$(curl -s "https://timor.tech/api/holiday/info/$(date -d 'tomorrow' +%Y-%m-%d)")
if echo "$response" | grep -q '"holiday":false'; then
  echo "明天是工作日，需要上班"
else
Confidence
95% confidence
Finding
This example operationalizes external API use in a workflow decision, meaning an agent could automatically transmit date information and act on unverified third-party responses. The risk is amplified slightly because the returned data directly affects behavior, so outages, tampering, or inaccurate responses could lead to incorrect automation decisions in addition to privacy leakage.

Missing User Warnings

Low
Confidence
93% confidence
Finding
The skill instructs users/agents to query a third-party API but does not warn that requested dates, IP address, user-agent, and access timing metadata will be disclosed to timor.tech. While the transmitted data is usually low sensitivity, the omission creates a real privacy/transparency issue and may violate expectations or policy in constrained environments.

Static analysis

No suspicious patterns detected.