ClawHub
Back to skill

Security audit

agent-harness-architect

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-first architecture-design skill whose file writing and network use are disclosed, user-confirmed, and aligned with maintaining its own reference knowledge base.

Install only if a Chinese-first Agent Harness architecture workflow fits your needs. Before allowing network research or knowledge-base updates, review the proposed sources and diffs, because those updates can influence future architecture recommendations.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The template is written entirely in Chinese and frames outputs as a fixed Chinese-language design document without any indication that language should follow the user's preference. In an agent skill, this can override user intent, reduce usability for non-Chinese users, and cause downstream integration or review failures when teams expect output in another language.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The file is entirely written in Chinese and presents fixed user-facing capability-boundary language without indicating any option to adapt to the user's preferred language or locale. In an agent skill, this can cause misunderstanding of safety boundaries, consent, or limitations for non-Chinese-speaking users, which weakens transparency and can lead to misuse or incorrect reliance on the skill.

Static analysis

No suspicious patterns detected.