ClawHub
Back to skill

Security audit

News Summary Litiao

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward news-summary helper that fetches public RSS feeds and optionally uses OpenAI text-to-speech for audio briefings.

Installers should know that text-only summaries use public RSS feeds, while voice summaries send the generated briefing text to OpenAI for speech generation and require an OPENAI_API_KEY. Avoid including private notes or sensitive user context in a voice briefing unless that data transfer is intended.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description says the skill should be used when the user asks for "news updates, daily briefings, or what's happening in the world." Phrases like "daily briefings" and especially "what's happening in the world" are broad conversational language and the file does not provide tighter trigger constraints or negative examples to limit unintended invocation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The voice-summary workflow instructs sending generated summary text to an external TTS API, but it does not require explicit user consent or warn that content will leave the local environment. If summaries ever include sensitive user-provided context, preferences, or private data mixed into the briefing, that information could be transmitted to a third party without the user's awareness.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The referenced OpenAI endpoint confirms that the skill depends on an external service for audio generation, which means generated content leaves the current environment. In the context of a news skill this is less dangerous than arbitrary file exfiltration, but it still creates a genuine outbound data-flow risk if user-originated or sensitive text is ever included.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

  1. Send as audio message
bash
curl -s https://api.openai.com/v1/audio/speech \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The referenced OpenAI endpoint confirms that the skill depends on an external service for audio generation, which means generated content leaves the current environment. In the context of a news skill this is less dangerous than arbitrary file exfiltration, but it still creates a genuine outbound data-flow risk if user-originated or sensitive text is ever included.

Content

Scanner excerpt · SKILL.md (reported line 70)May include surrounding context.

  1. Send as audio message
bash
curl -s https://api.openai.com/v1/audio/speech \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{

Static analysis

No suspicious patterns detected.