ClawHub
Back to skill

Security audit

Rss Digest

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed RSS digest helper that uses an external feed tool to fetch and summarize posts, with no evidence of hidden or destructive behavior.

Install this if you are comfortable trusting the external `feed` CLI and having the agent fetch RSS/article content. Ask the agent to confirm before importing the starter OPML if you do not want it to add default feed subscriptions automatically.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill advertises itself for broad, everyday requests like 'what's new or interesting today' and general news catch-up, which can cause it to trigger in many common conversations without the user explicitly asking to use RSS tooling. That over-broad routing increases the chance the agent invokes external feed/network actions unexpectedly, expanding attack surface and creating opportunities for prompt-based data exfiltration or untrusted content ingestion from RSS feeds.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.