Persistent Mind

Provides persistent, searchable, context-aware memory storage for AI agents to retain user preferences, corrections, and project context across sessions.

This skill appears to be what it says: a local persistent memory manager that stores data under .persistentmind/ and does not request credentials or network access. Before installing or using it: 1) Audit the included source (persistentmind.py) yourself or have someone you trust review it; while the imports shown are standard-library only, a full review ensures there are no hidden network calls or dynamic imports. 2) Do not store secrets (API keys, passwords, private tokens) in memories unless you accept the risk; exported JSON (export_memories) and imports are plaintext and can leak secrets. 3) Protect the storage directory: exclude .persistentmind/ from version control, set restrictive filesystem permissions (e.g., chmod 700), and consider encrypting sensitive items before storing. 4) When using team sharing, verify recipients and scrub any sensitive content first. 5) If you need secret retention, prefer a dedicated secret manager with access controls rather than this general-purpose memory. If you want more assurance, ask the publisher for a signed release or run static/dynamic analysis to confirm there are no outbound network calls and that export/import functions sanitize inputs.

Type: OpenClaw Skill Name: persisent-mind Version: 1.0.0 The OpenClaw AgentSkills skill bundle 'PersistentMind' is classified as benign. All files (SKILL.md, persistentmind.py, manifest.yaml, LICENSE.md, README.md) consistently describe and implement a local-only, zero-dependency memory system for AI agents. The Python code (`persistentmind.py`) strictly adheres to its stated privacy and security claims: all data is stored locally within a `.persistentmind/` directory, there are no external network calls, no sensitive environment variables are read, and no dangerous system commands are executed. The `SKILL.md` and `README.md` clearly explain the skill's functionality, including how it injects context into prompts, which is a feature for the agent's benefit, not a prompt-injection attack against it. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or obfuscation.