ClawHub

Daily Astro

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed daily horoscope skill with optional scheduled pushes and no evidence of hidden data access, exfiltration, destructive behavior, or unrelated authority.

Install if you want horoscope generation and optional scheduled push messages. Review the push settings before enabling them, use the provided off command to disable scheduled messages, and narrow activation phrases in your agent if generic astrology terms trigger the skill too often.

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 (3)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger list is very broad and includes generic terms like "horoscope," "zodiac," and many sign names, which can cause the skill to activate in contexts where the user did not intend to invoke it. In a chat-assistant environment, this can lead to prompt hijacking of ordinary conversations, noisy activations, and accidental disclosure or processing of user context by the skill.

Natural-Language Policy Violations

Low
Confidence
68% confidence
Finding
The README advertises bilingual EN/CN output as a fixed behavior without indicating language preference detection or user opt-in. While not a severe security flaw, forced dual-language responses can create privacy and usability issues in shared channels, increase unintended data exposure to broader audiences, and reduce user control over output handling.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The invocation examples are broad enough to trigger on generic horoscope-related phrases, including adjacent topics like compatibility or advice about relationships and contracts. In an agent environment, overly broad activation can cause unintended routing, unexpected skill execution, or the skill responding in contexts where the user did not clearly request astrology content.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal