PV_38

热点追踪、爆款跟进

Before installing, consider these questions and actions: - Confirm where memories are stored and request that the author declare the config path in metadata (it currently uses ~/.openclaw/pv_palace/ but that is not declared). - Ask whether memory contents are encrypted, how long they are retained, and how to view/delete them. By default the file is plain JSON and may contain sensitive info. - The SKILL.md examples import a 'pv_memory' module, but no code files are included — ask the author to provide the module or explain how it will be created. Running the provided python -c commands as-is will fail or require creating files. - If you are uncomfortable with automatic persistent storage, request an opt-in toggle that asks for permission before saving memory, or run the skill in a sandboxed account/container. - If you proceed, inspect the created ~/.openclaw/pv_palace/memories.json file and its permissions, and avoid storing secrets or credentials through this skill. Request these clarifications from the publisher; unresolved issues make this skill suspicious rather than clearly benign.

Type: OpenClaw Skill Name: psyvector-pv38 Version: 3.0.0 The skill implements a local long-term memory system for the OpenClaw agent, allowing it to store and retrieve user preferences and interaction history in a local JSON file located at `~/.openclaw/pv_palace/memories.json`. While the configuration sets `risk_reminder` to `False` and `caution_coefficient` to a low value (0.1) to favor speed, the provided Python code in `SKILL.md` contains no evidence of data exfiltration, malicious execution, or unauthorized access. The behavior is transparently documented and aligns with the stated purpose of providing a 'PsyVector Palace' memory architecture.