ClawHub
Back to skill

Security audit

RSS阅读器免费版

Security checks across malware telemetry and agentic risk

Overview

This is a mostly coherent RSS/Atom reader skill, with some broad wording and persistence examples users should apply carefully.

Install only if you want an agent to run local Node.js commands and access RSS/Atom feed URLs you configure. Review any cron or file-output examples before using them, choose non-sensitive output locations, and treat the broad writing/marketing trigger as limited to content ideas derived from configured feeds.

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 (2)

Vague Triggers

High
Confidence
90% confidence
Finding
The trigger condition says the skill should be used for broad writing and marketing tasks, which exceeds the documented RSS-reading scope and can cause the agent to invoke this skill for unrelated, common requests. In an agent ecosystem, overly broad routing can lead to unnecessary execution of local commands and network-fetching behavior when the user did not intend to use this tool.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The documentation includes examples that redirect output to files and schedule periodic execution via crontab, but it does not warn about overwriting existing files, storing potentially sensitive feed-derived content, or repeated unattended network activity. In practice, this can cause accidental data loss or unintended persistence/exfiltration surfaces if users adapt the examples without safeguards.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.