ClawHub
Back to skill

Security audit

Opencode Omo

Security checks for vulnerabilities and agentic risk

Overview

This is a simple workflow guide for using OpenCode agents on coding tasks, with no bundled executable code or hidden persistence.

Install only if you already intend to use OpenCode and Oh-My-OpenCode for coding automation. Run it in the intended repository, review diffs and commands before accepting changes, and note that the referenced helper scripts were not present in this artifact.

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
  • 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
89% confidence
Finding
The skill advertises that it will 'turn coding requests into completed work' and repeatedly encourages direct execution workflows, but it does not define boundaries on repository scope, privileged operations, dependency changes, secret handling, or approval gates. In an agentic coding environment, this broad activation scope can cause the system to act on ambiguous or unsafe prompts, increasing the chance of destructive edits, insecure code generation, or unintended command execution.

Static analysis

No suspicious patterns detected.