ClawHub
Back to skill

Security audit

Rss Reader Ai Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed RSS summarization and notification helper, with normal privacy precautions needed for API keys and outbound delivery.

Install only if you are comfortable sending selected feed content or generated summaries to your chosen LLM and notification provider. Keep API keys and email credentials in environment variables or a secret manager, review any missing implementation files before running them, and test with one-time execution before enabling a schedule.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger condition is framed so broadly ('需要AI模型调用、智能对话、Agent编排、LLM应用时使用') that an agent could invoke this skill for many unrelated requests, not just RSS aggregation. Overbroad activation increases the chance of unintended network access, content fetching, summarization, and outbound delivery using configured credentials, which is a real security and privacy boundary issue for an agent-executable skill.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The overview describes AI summarization and push delivery but does not clearly warn that fetched article content, feed metadata, and possibly user-configured data will be transmitted to third-party LLM and notification providers. This omission can mislead users about data flow and trust boundaries, causing inadvertent disclosure of browsing interests, content, or other sensitive information to external services.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs users to configure API keys, webhooks, bot tokens, chat IDs, and email credentials, but does not pair that with an explicit security warning about secret handling and outbound transmission. In an agent/tool-use context, exposing these integrations without clear safeguards raises risk of credential leakage, accidental misuse, or sending fetched content to external endpoints the user may not fully trust.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.