PV_37

舆论攻防、危机公关

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.

Type: OpenClaw Skill Name: psyvector-pv37 Version: 3.0.0 The skill bundle contains aggressive language in SKILL.md, specifically instructions to 'Violently attack and lock the system' (猛烈攻击锁死系统) and a very low 'caution_coefficient' (0.1), which suggests potential for harmful or uncontrolled behavior. While the provided Python code for the 'PsyVector Palace' memory system is functionally benign (storing data locally in ~/.openclaw/pv_palace/), the combination of the aggressive persona and the lack of safety constraints is concerning. No evidence of data exfiltration or unauthorized remote execution was found in the provided snippets.