ClawHub
Back to skill

Security audit

Databox

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Databox connector guide with disclosed write/delete actions, though users should verify the external CLI installer before using it.

Before installing, confirm you trust OOMOL and the oo CLI installation source, use verified installer instructions where possible, and review any Databox write or delete payload before approving it.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs users to install software via curl ... | bash, which executes a remote script directly without verification, pinning, checksum validation, or signature checking. If the remote host, transport path, or served installer is compromised, this can lead to arbitrary code execution on the user's machine.

Content

Scanner excerpt · SKILL.md (reported line 61)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger text says to use this skill for "ANY Databox request" and "instead of calling the API directly," which is overly broad and can cause the agent to invoke this skill for all Databox-related tasks without narrower scoping or additional safety checks. In context, this increases the chance that write or destructive connector actions are selected when a safer read-only path or a more specific workflow should have been used.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.