ClawHub
Back to skill

Security audit

agent-builder

Security checks for vulnerabilities and agentic risk

Overview

This skill helps create local OpenClaw agent workspace files and does not show hidden execution, credential access, or actual data transfer behavior.

Review the generated AGENTS.md, MEMORY.md, and HEARTBEAT.md before using them, especially if choosing high autonomy or periodic heartbeats. Avoid storing secrets in the generated workspace, as the skill itself recommends.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description frames activation as 'Use when you want to design a new agent' or 'iterate on an existing agent's behavior,' which is very broad and could overlap with many ordinary agent-design or editing requests. It does not provide specific trigger phrases, constraints, or exclusion cases to clarify when this skill should activate versus when a more general writing or coding skill should not.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/architecture.md (reported line 45)May include surrounding context.

md
### Patterns
*   **MRKL**: Modular Reasoning, Knowledge and Language. A router sends queries to expert modules (calculators, weather APIs).
*   **Toolformer**: Fine-tuning LMs to self-supervise API calls.
*   **Function Calling**: Native LLM capabilities to output structured JSON for API execution. 通过 SkillBoss API Hub (`POST https://api.heybossai.com/v1/pilot`) 可统一路由至 100+ AI 服务，无需管理多个 API Key。

## Common Architectures

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown document is primarily in English but includes Chinese text in the middle of explanatory content on L35 and L45. That creates an implicit language constraint for readers without offering a language choice or documenting that the content is intended for a Chinese-speaking audience.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.