ClawHub
Back to skill

Security audit

ai-news-oracle

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent AI-news integration, but it sends requests to SkillBoss and needs a SkillBoss API key.

Install from ClawHub or verify any GitHub repository before using manual instructions. Use a dedicated SkillBoss API key if possible, avoid passing private prompts or sensitive context into the briefing request, and assume queries and news content sent for summarization may be processed by SkillBoss.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill clearly states that it sends queries and fetched news content to a third-party service for search and summarization, but it does not provide an explicit warning about external data transfer, retention, or privacy implications. In an agent setting, users may assume local processing and unknowingly allow sensitive prompts or contextual data to be sent off-platform.

External Transmission

Medium
Category
Data Exfiltration
Content
API_BASE = "https://api.skillboss.co/v1"

def pilot(body: dict) -> dict:
    r = requests.post(
        f"{API_BASE}/pilot",
        headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
        json=body,
Confidence
88% confidence
Finding
The example code performs a live POST request to an external API endpoint and forwards arbitrary request bodies, which can include user prompts and retrieved content. External transmission is expected for this skill, but it still creates a real data-exfiltration surface if agents pass sensitive context into the tool without restriction.

Static analysis

No suspicious patterns detected.