ClawHub
Back to skill

Security audit

daily-info

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent date and weather helper, but its weather instructions include unsafe shell-based lookups for user-supplied city names that should be reviewed before use.

Install only if you are comfortable with live weather queries being sent to third-party services. The skill should be revised to use a structured HTTPS request method, URL-encode or validate city names, avoid shell interpolation of user input, and explicitly use https:// for wttr.in before routine use.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:32
Finding

Shell Command Injection Through an Unvalidated User-Supplied City Name

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:32
Finding

Weather Requests Use an Implicit Plaintext HTTP Scheme

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill’s trigger scope is very broad, covering common requests about date and weather that occur frequently in normal conversation. This can cause over-triggering, unnecessary external lookups, and unintended routing to this skill when the user did not explicitly ask for it, increasing privacy and reliability risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill hardcodes Chinese-language weather output via lang=zh without checking the user’s language preference. This can produce mismatched output, degrade usability, and in multilingual contexts may cause the agent to ignore user expectations or platform language settings.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
79% confidence
Finding

The skill instructs the agent to send data to an external weather API, which constitutes outbound transmission to a third party. Even if the transmitted data is limited to coordinates or city names, it can disclose user location preferences or inferred location context to an external service without any privacy notice or minimization guidance.

Content

Scanner excerpt · SKILL.md (reported line 60)May include surrounding context.

Open-Meteo（程序化获取）： 需要先获取城市坐标，然后查询：

bash
curl -s "https://api.open-meteo.com/v1/forecast?latitude=30.6&longitude=114.3¤t_weather=true&hourly=relativehumidity_2m,apparent_temperature,uv_index&timezone=Asia/Shanghai"

天气详情项