ClawHub
Back to skill

Security audit

AI Insights

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-news report generator that uses web search and saves a Markdown report to a fixed local path.

Install this if you want Chinese AI-news insight reports. Expect it to perform several web searches and create a Markdown report under ./artifacts/ai-insights-report/. Only configure the optional cron-based daily push if you intentionally want scheduled recurring reports.

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

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description mandates Chinese behavior and says the skill outputs a structured report in Markdown, while the entire trigger and usage text is Chinese-only. This creates a language/locale constraint without user opt-in or a documented region-specific justification, which matches the policy-violation category.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs the agent to write a generated report to a local filesystem path without explicitly warning the user that a file will be created. While the path is fixed and not obviously attacker-controlled, silent file creation can violate user expectations, create privacy/retention issues, and become more risky in environments where local artifacts are synced or exposed.

Content

No source excerpt is available for this finding.