ClawHub
Back to skill

Security audit

Amilia

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed, read-only Amilia connector that uses OOMOL's CLI and does not show hidden, destructive, or unrelated behavior.

Install this only if you want your agent to read Amilia program and activity data through your OOMOL-connected Amilia account. Review the first-time setup steps before use, especially the OOMOL CLI login and Amilia connection, and keep use limited to the listed read actions unless a future version adds clearly disclosed write actions.

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
88% confidence
Finding
The description instructs use of this skill for "ANY Amilia request," which is broader than the concrete capabilities listed in the skill and can cause the agent to invoke it in situations where direct API use or another skill would be more appropriate. Overbroad routing increases the chance of unintended data access or tool execution, especially when a user request is ambiguous or includes mixed-provider tasks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.