ClawHub
Back to skill

Security audit

Rss Ai Reader

Security checks across malware telemetry and agentic risk

Overview

This skill matches its stated RSS summarization and notification purpose, but users should review the linked code and protect their API keys before running it.

Before installing, review the referenced GitHub repository and requirements, prefer a pinned commit for repeat use, store secrets in environment variables or a vault, use least-privilege webhooks/bot tokens/app passwords, test with --once first, and only process feeds whose contents may be sent to the selected AI and notification services.

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
Confidence
94% confidence
Finding
The trigger phrases are broad enough to match many ordinary requests about news, websites, and summaries, which can cause the skill to activate when the user did not explicitly intend to use this external RSS/LLM workflow. In this skill’s context, unintended activation is more dangerous because it may fetch third-party content, invoke external LLM providers, and send outputs to push channels, creating privacy and consent risks.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill description does not warn users that feed contents may be transmitted to external LLM providers and that notification integrations require sensitive credentials such as API keys, webhooks, bot tokens, or SMTP settings. In this context, the omission increases the chance that users expose internal feed data or secrets without understanding the data flow to third-party services.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.