ClawHub
Back to skill

Security audit

Daily Ai News Skill 0.1.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward AI news briefing helper that uses external news sites and web search as expected, without hidden persistence, code execution, or sensitive local access.

Install this if you want live AI news briefings. Be aware it will contact third-party news sites and search providers when used, so avoid including private or sensitive context in news requests unless your environment permits external browsing.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation criteria are broad enough to match many generic AI-interest requests, which can cause the skill to trigger unexpectedly and perform external web fetches/searches without the user clearly intending a news-browsing workflow. In this skill, that ambiguity matters because activation leads directly to third-party network access and content aggregation, increasing the chance of overreach, surprise data flow, or irrelevant tool use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs the agent to fetch from multiple external sites and run web searches, but it does not clearly disclose this behavior to the user before or at activation. This can create a transparency and consent problem, especially in environments where users may expect a local answer rather than third-party requests and link collection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.