ClawHub
Back to skill

Security audit

Bolna

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent OOMOL connector wrapper for read-only Bolna workspace operations, with no artifact-backed malicious behavior found.

Install this only if you intend to use OOMOL's oo CLI with your connected Bolna account. The skill can read Bolna agents, execution history, raw execution logs, and workspace/user wallet summaries, so treat outputs as potentially sensitive and review any future write or destructive actions 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
90% confidence
Finding
The skill description says to use this skill for ANY Bolna request instead of calling the API directly, which is an overly broad invocation trigger. This can cause the agent to route all Bolna-related tasks through a shell-enabled skill even when a narrower or safer path would be more appropriate, increasing unnecessary exposure to command execution and connector misuse.

Static analysis

No suspicious patterns detected.