ClawHub
Back to skill

Security audit

Hamsa

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, read-only Hamsa connector through the OOMOL CLI, with setup and authentication steps that are conditional rather than automatic.

Before installing, understand that this skill can read data from the Hamsa account connected to OOMOL through the oo CLI. Only run setup or login steps when needed, and review any future added write or destructive actions carefully before approving them.

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
94% confidence
Finding
The description says to use this skill for "ANY Hamsa request" and "instead of calling the API directly," which is an overly broad trigger that can cause the agent to invoke the skill in situations where a narrower or safer mechanism would be more appropriate. Because the skill has shell access via `Bash(oo *)` and includes setup/authentication guidance, broad auto-selection increases the chance of unintended command execution or unnecessary exposure of connected-account data.

Static analysis

No suspicious patterns detected.