ClawHub
Back to skill

Security audit

dakboard

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward DAKboard control script, with a notable caution that the API key is sent to DAKboard in request URLs.

Install only if you trust DAKboard with the data you ask the agent to display or change. Use a dedicated, revocable DAKboard API key if possible, and be aware that this implementation places the key in request URLs, which can increase exposure through logs or diagnostics.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/dakboard.py:34
Finding

DAKboard API Credential Exposed in URL Query String

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill requires access to environment variables and makes outbound network requests, but it does not declare an explicit tool scope such as permissions or allowed-tools. This weakens enforcement boundaries for autonomous invocation and makes it easier for the agent runtime to grant broader capabilities than users or operators may expect, especially since the skill uses a secret API key and can send user-provided data to an external service.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.