ClawHub
Back to skill

Security audit

News Summary

Security checks for vulnerabilities and agentic risk

Overview

This news-summary skill is coherent and purpose-aligned, with the main privacy consideration being optional cloud text-to-speech for generated news summaries.

Install this if you want RSS-based news summaries and optional voice output. Use text-only mode for private contexts, and only request voice generation when you are comfortable sending the final news-summary text to OpenAI for speech synthesis.

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
89% 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 natural-language requests that could match everyday conversation without clearly delimiting when this skill should or should not activate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs sending generated summary text to an external TTS API without requiring explicit user notice or consent for external transmission. If the summary ever contains user-provided or sensitive contextual content, this can expose data to a third-party service unexpectedly, making the issue contextually meaningful even though the primary use case is public news.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The presence of the external OpenAI endpoint confirms third-party transmission capability. While expected for cloud TTS, the lack of guardrails around what may be sent means the skill could disclose more than intended, so the finding is a real privacy/security concern rather than a pure false positive.

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
89% confidence
Finding

The presence of the external OpenAI endpoint confirms third-party transmission capability. While expected for cloud TTS, the lack of guardrails around what may be sent means the skill could disclose more than intended, so the finding is a real privacy/security concern rather than a pure false positive.

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.