ClawHub
Back to skill

Security audit

dorodango

Security checks for vulnerabilities and agentic risk

Overview

This skill is a code-polishing workflow that may edit target code and keep a small local resume file, with no hidden executable payloads found.

Install only if you want an agent-guided code refinement workflow. Expect it to run tests, edit the target code you provide, and create or update `.attune/dorodango-state.json` with polishing progress for resume support.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file states that the skill tracks state in .attune/dorodango-state.json, which means the skill persists data to disk across sessions. The description explains the mechanism but does not explicitly warn the user that running the workflow will create or update a file in the workspace.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.