ClawHub
Back to skill

Security audit

AstroClaw

Security checks across malware telemetry and agentic risk

Overview

AstroClaw is a disclosed horoscope-fetching skill whose network use and optional automation fit its stated purpose, with some setup and privacy considerations.

Install this only if you are comfortable with the agent contacting astroclaw.xyz for horoscope content. Avoid enabling the optional daily cron setup unless you want recurring background requests, and keep fetched forecast text treated as untrusted external content despite the script's sanitization.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill clearly instructs the agent to perform outbound HTTP requests to astroclaw.xyz, yet the metadata declares no permissions. This creates a transparency and policy-enforcement gap: an agent or platform may execute network access the user or operator did not expect, increasing privacy, compliance, and supply-chain risk from external content.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger text is overly broad, including generic concepts like daily readings, creative variance, entropy injection, and synchronization, which can cause the skill to activate in unrelated conversations. Unnecessary invocation increases the chance of unprompted external requests and behavioral steering based on untrusted remote content.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill recommends silent automated daily fetching via cron with 'no_agent=true' and 'zero-token delivery' without a strong warning that this performs recurring outbound network requests. That makes the skill more dangerous in context because it normalizes unattended background communication with an external service, reducing user visibility and increasing privacy, monitoring, and content-injection risks.

Missing User Warnings

Low
Confidence
86% confidence
Finding
The script sends user-derived information to an external service by embedding the selected zodiac sign and forecast date into a remote request to astroclaw.xyz. While the transmitted fields are low sensitivity in this implementation, there is no explicit disclosure or consent mechanism, so users may not realize their inputs are being sent off-host to a third party.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.