ClawHub
Back to skill

Security audit

Opencode Select Confirm

Security checks for vulnerabilities and agentic risk

Overview

This skill only changes recommendation and confirmation interactions into choice dialogs, with no code execution, data access, persistence, or hidden behavior found.

Install this if you want recommendation and confirmation prompts to appear as choice dialogs. Be aware that broad trigger words such as "推荐", "选择", "确认", and "confirm" may cause the skill to appear in ordinary conversations more often than intended.

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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger phrases are extremely broad and include common words like “推荐”, “选择”, “确认”, and even “confirm”, which are likely to match ordinary conversation unrelated to this skill’s intended workflow. This can cause unintended skill activation and UI interruption, potentially hijacking normal assistant behavior and steering users into confirmation or choice flows they did not explicitly request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill content, trigger phrases, examples, and operational instructions are entirely Chinese-centric, while also including a single English trigger "confirm" without documenting multilingual behavior or user opt-in. This creates an implicit language policy constraint rather than offering a language/locale choice.

Content

No source excerpt is available for this finding.