ClawHub
Back to skill

Security audit

daily-every

Security checks for vulnerabilities and agentic risk

Overview

This is a small daily briefing skill that fetches public weather and V2EX data and sends a Telegram brief, with no bundled code or hidden install behavior.

Before installing, confirm you want an automated daily brief that contacts wttr.in and v2ex.com and sends the result through Telegram. Configure Telegram credentials carefully and only enable the cron trigger if you want unattended messages.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly performs outbound network requests to third-party services and then pushes the aggregated result to Telegram, but it does not disclose these transmissions or require clear user/operator awareness. This creates a real transparency and privacy issue: execution causes data to leave the local environment and may trigger external messaging side effects, which is especially relevant for cron-based autonomous runs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The natural-language instructions specify Chinese trigger phrases and present the skill behavior in Chinese, which can amount to a language policy constraint if users are not given an explicit choice. There is no stated opt-in or justification that this skill is intended only for Chinese-speaking or region-specific use.

Content

No source excerpt is available for this finding.