ClawHub
Back to skill

Security audit

Amara

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a disclosed Amara account connector, with one routing caution but no evidence of hidden or malicious behavior.

Install this only if you want an agent to operate your Amara account. Require explicit user intent before using the skill, and review or confirm any action that creates, updates, or deletes Amara data.

SkillSpector

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
92% confidence
Finding
The skill description says to use this skill for ANY Amara request, which is an overly broad trigger that can cause the agent to invoke the skill whenever Amara is mentioned, even if the user did not intend to operate on their connected account. In this context the skill includes both read and write/destructive actions, so over-triggering can route sensitive or state-changing requests through a powerful integration unnecessarily.

Static analysis

No suspicious patterns detected.