Back to skill

Security audit

Hive Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a planning and scaffolding guide for a Hive-style OpenClaw workflow, and its higher-impact actions are disclosed as opt-in activation steps rather than automatic behavior.

Before installing, understand that this skill is meant to create a persistent Hive scaffold under your workspace and can later guide specialist execution. Use it first for planning or contained scaffolding, and only approve live activation, routing changes, or specialist spawning when you actually want Hive to influence your workflow.

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
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 (5)

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 · README.md (reported line 391)May include surrounding context.

md
### #1 HRM (`hive-hrm`)
- Hiring + workflow design
- Proposes new specialist roles and chains
- Should not auto-deploy structural changes without approval

### #2 OPS (`hive-ops`)
- External environment matching and operational checks

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 282)May include surrounding context.

md
### #1 HRM (`hive-hrm`)
- Hiring + workflow design
- Proposes new specialist roles and chains
- Should not auto-deploy structural changes without approval

### #2 OPS (`hive-ops`)
- External environment matching and operational checks

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
85% 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 282)May include surrounding context.

md
### #1 HRM (`hive-hrm`)
- Hiring + workflow design
- Proposes new specialist roles and chains
- Should not auto-deploy structural changes without approval

### #2 OPS (`hive-ops`)
- External environment matching and operational checks

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The document leads with a Chinese-first presentation and places English behind an anchor link, which can be read as a default language choice rather than an explicit user-selected preference. The policy calls for flagging language or locale constraints when they are imposed without opt-in or justified region specificity.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The markdown includes HIVE-合规专员-扩员.md as a bundled template, which introduces a specific non-English language artifact in the skill's default materials. There is no nearby note offering language selection or explaining that mixed-language templates are optional, so this may violate a language/locale policy requiring user choice.

Content

No source excerpt is available for this finding.