ClawHub
Back to skill

Security audit

My Daily Brief

Security checks for vulnerabilities and agentic risk

Overview

This is a simple daily brief skill that fetches public weather and Baidu hot-topic information, with minor clarity issues but no deceptive or high-impact behavior.

Install only if you want a China-focused daily brief using Beijing weather and Baidu hot-search results. Be aware that the skill text has inconsistent schedule wording and does not ask for your location or preferred news source.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation conditions are broader than the stated skill purpose and include a generic phrase like '有什么新闻', which can cause the skill to trigger in situations where the user may have intended a different news or information workflow. In addition, the cron trigger in the body conflicts with the metadata timing, increasing the chance of unintended automatic execution and confusing behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The workflow hard-codes Beijing weather and Baidu hot searches without checking the user's location, language, or preferred news source. This can silently deliver inaccurate or region-specific results, creating privacy and relevance issues when the user's locale differs from the forced defaults.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.