PV_37

舆论攻防、危机公关

Security Scan

The skill's stated purpose (crisis PR /舆论攻防) aligns with features like persistent memory, but the runtime instructions quietly write persistent files to the user's home and include aggressive wording about 'attacking' defenses; the skill omits declaring the config path it uses and automatically storing user data without explicit consent, which is inconsistent and risks privacy/misuse.

Purpose & Capability

The declared purpose (舆论攻防、危机公关) is consistent with having a long-term memory and fast-response personality. However the SKILL.md contains explicit aggressive phrasing ('猛烈攻击锁死系统' / 'Attack defense') which suggests offensive tactics; while that can be coherent with 'public-opinion offense/defense', it raises ethical/use-case concerns that are not surfaced in the metadata.

Instruction Scope

The instructions include Python code that will create and modify a local file ~/.openclaw/pv_palace/memories.json and indicate these memory functions will be '自动调用' (automatically invoked). The skill metadata declared no required config paths, yet the runtime instructions read/write a specific filesystem path and instruct running python commands — a mismatch that affects privacy and scope.

Install Mechanism

This is an instruction-only skill (no install spec, no code files shipped). That minimizes installation risk because nothing is downloaded or installed by default; code snippets are provided for local execution but are not auto-installed by a package manager.

Credentials

No environment variables or external credentials are requested, which is reasonable, but the skill nevertheless persists arbitrary user content to a local path. The omission of that path from declared required config paths is an incoherence — the skill will access and modify user filesystem state but did not declare it.

Persistence & Privilege

The skill intentionally implements persistent storage (writing memories under ~/.openclaw/pv_palace/). Persisting its own data is normal for a memory-capable skill, but because the storage is automatic and not documented in the metadata, users should be aware this creates persistent state and possible sensitive-data retention.

What to consider before installing

Before installing or invoking this skill: (1) Understand it will automatically write persistent memories to ~/.openclaw/pv_palace/memories.json — inspect that file and path and ensure you are comfortable with data retention. (2) Ask the publisher (or inspect the full SKILL.md) whether automatic memory storage can be disabled or limited and whether stored data is encrypted. (3) Be cautious about using this skill for activities that could be offensive or manipulative; the skill's wording references 'attack' behaviors. (4) Because the metadata did not declare the filesystem path it uses, consider running the skill in a sandboxed environment or account with no sensitive data. (5) If you need assurance, request the publisher to declare required config paths and provide an explicit opt-out for persistent storage.

防御 AI

中文: 猛烈攻击锁死系统

English: Attack defense

配置参数

参数	值	说明
response_delay	0.2s	响应延迟
speech_speed	0.75	语速倍率
caution_coefficient	0.1	谨慎系数
risk_reminder	True	风险提醒

使用方法

clawhub install psyvector-pv37

人格说明

动量型内核 - 快速响应，高频交易，危机处理

🧠 长期记忆能力

本数字员工具备持久记忆功能，自动记住用户偏好、决策和重要信息。

记忆存储 (自动调用)

import os, json, hashlib
from datetime import datetime

PALACE_PATH = os.path.expanduser("~/.openclaw/pv_palace/")

def store_memory(content, importance=5, tags=None):
    """存储记忆到本地宫殿"""
    os.makedirs(PALACE_PATH, exist_ok=True)
    path = os.path.join(PALACE_PATH, "memories.json")
    
    data = {"memories": [], "index": {}} if not os.path.exists(path) else json.load(open(path))
    
    mem_id = hashlib.sha256(f"{content}{datetime.now().isoformat()}".encode()).hexdigest()[:12]
    memory = {"id": mem_id, "content": content, "importance": importance, 
              "tags": tags or [], "created_at": datetime.now().isoformat()}
    
    data["memories"].append(memory)
    for tag in (tags or []):
        data["index"].setdefault(tag, []).append(mem_id)
    
    json.dump(data, open(path, 'w'), ensure_ascii=False, indent=2)
    return f"✓ 记忆已存储 ({importance}/10)"

记忆搜索 (自动调用)

def search_memories(query, limit=5):
    """搜索记忆"""
    path = os.path.join(PALACE_PATH, "memories.json")
    if not os.path.exists(path):
        return []
    
    data = json.load(open(path))
    results = [m for m in data["memories"] if query.lower() in m["content"].lower()]
    results.sort(key=lambda x: x.get("importance", 0), reverse=True)
    return results[:limit]

获取上下文摘要

def get_context(limit=10):
    """获取记忆上下文"""
    path = os.path.join(PALACE_PATH, "memories.json")
    if not os.path.exists(path):
        return "暂无记忆"
    
    data = json.load(open(path))
    memories = sorted(data["memories"], key=lambda x: x.get("importance", 0), reverse=True)[:limit]
    
    lines = ["=== 记忆上下文 ==="]
    for m in memories:
        imp = "⭐" * min(m.get("importance", 5), 5)
        tags = ", ".join(m.get("tags", [])[:3])
        lines.append(f"{imp} {m['content'][:60]}")
        if tags:
            lines.append(f"   [{tags}]")
    return "\n".join(lines)

使用场景

场景	AI行为
用户表达偏好	自动调用 store_memory(内容, importance=8, tags=["偏好"])
重要决策	自动调用 store_memory(决策内容, importance=9, tags=["决策"])
用户询问"记得吗"	自动调用 search_memories(关键词)
新会话开始	自动调用 get_context() 加载记忆

执行命令

# 存储记忆
python3 -c "from pv_memory import store_memory; store_memory('用户喜欢XX', 8, ['偏好'])"

# 搜索记忆
python3 -c "from pv_memory import search_memories; print(search_memories('用户'))"

# 查看上下文
python3 -c "from pv_memory import get_context; print(get_context())"

---

本数字员工配备持久记忆系统，基于PsyVector Palace架构