ClawHub
Back to skill

Security audit

Arrive Guideline Architect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ARRIVE protocol generator/checker that reads study inputs and writes protocol/checklist files, with no evidence of hidden persistence, credential access, exfiltration, or destructive behavior.

Before installing, note that the skill can run Bash and write files, so use it on study documents you intend to process and review generated protocols for local ethics committee and statistical requirements. The included examples are partly Chinese, but I found no evidence of hidden network access, credential use, persistence, or destructive actions.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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)

Memory Manipulation

High
Category
Memory Poisoning
Content
检查日期: 2026-02-06

## 1. Study Design
描述: For each experiment, provide brief details of study design including: the number of experimental and control groups; the number of animals per group; and a clear statement of whether the experiment was performed blinded.

检查要点:
  ☐ 明确实验组和对照组数量
Confidence
80% confidence
Finding
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Memory Manipulation

High
Category
Memory Poisoning
Content
检查日期: 2026-02-06

## 1. Study Design
描述: For each experiment, provide brief details of study design including: the number of experimental and control groups; the number of animals per group; and a clear statement of whether the experiment was performed blinded.

检查要点:
  ☐ 明确实验组和对照组数量
Confidence
80% confidence
Finding
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
This markdown file is written almost entirely in Chinese, with no indication that the user can choose another language or that the language restriction is required by a documented regional context. The policy specifically calls for flagging language or locale constraints when they are imposed without user opt-in.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
This JSON manifest contains human-readable title, study fields, and protocol descriptions in Chinese, but there is no accompanying indication that Chinese output is optional or restricted to a documented locale-specific context. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern applicable to all file types.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
This markdown file contains substantial instructional content in Chinese while also embedding English headings and descriptions, but it does not state that the checklist is intended for a Chinese-speaking audience or offer an alternative language option. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy issue.

Static analysis

No suspicious patterns detected.