ClawHub
Back to skill

Security audit

Altiria

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed Altiria connector that can read and change account data, with user-confirmation requirements for write and delete actions.

Install only if you want your agent to operate your connected Altiria account through OOMOL. Read-only actions can run directly, but creating or updating contacts, sending SMS messages, and deleting contacts should be done only after you verify the exact payload and target.

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
91% confidence
Finding
The skill description says to use this skill for ANY Altiria request, which creates an overly broad trigger surface and can cause the agent to route all Altiria-related tasks through a high-privilege integration without finer scoping. In context, this skill supports read, write, and destructive actions, so broad invocation increases the chance of unintended state-changing operations being selected or attempted when a narrower, task-specific workflow would be safer.

Static analysis

No suspicious patterns detected.