ClawHub
Back to skill

Security audit

Opencode-controller

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill gives disclosed, user-confirmed instructions for operating Opencode and does not add hidden code, persistence, or unrelated data access.

Before installing, understand that this skill routes coding work through Opencode and may reuse Opencode session history for the current project. It should ask you to choose a provider, confirm authentication, approve new sessions, and confirm login completion before continuing.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
### Login link does not work
- Ask the user to retry
- Do not proceed without confirmation

### Model not available
- Inform the user

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/failure-handling.md (reported line 5)May include surrounding context.

md
### Login link does not work
- Ask the user to retry
- Do not proceed without confirmation

### Model not available
- Inform the user

Static analysis

No suspicious patterns detected.