ClawHub
Back to skill

Security audit

Agent Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a local markdown-only skill for designing OpenClaw agent workspaces, with disclosed memory and heartbeat options and no automatic external actions.

Review the generated agent files before using them, especially any MEMORY.md or HEARTBEAT.md content and any autonomy setting. Avoid enabling broad autonomy, outbound messaging, or periodic heartbeat checks until the agent's rules are clear and tested.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

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
92% confidence
Finding

This markdown file is primarily written in English, but line 35 introduces Chinese text without user opt-in or explanation of a bilingual/localized policy. That can violate a language/locale policy when a skill or reference document implicitly forces mixed-language content on users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

Line 45 contains Chinese explanatory text embedded in an otherwise English document, with no indication that the document is intended for Chinese-speaking users or bilingual audiences. This is a natural-language locale inconsistency under the language/locale policy criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.