Procedural Memory

Inspired by Hermes Agent's procedural memory system. When a workflow works, save it as a reusable skill. Triggered when: (1) user says 'remember this workflo...

This skill is plausible for saving reusable workflows, but review and consider the following before installing: - Consent & auto-creation: SKILL.md says it will auto-create a skill (write files) if the same workflow succeeds 3+ times without asking. If you do not want the agent to create persistent artifacts without explicit approval, edit/remove that auto-create rule. - Privacy: the skill scans conversation history and writes derived summaries to disk (~/.openclaw/workspace/skills and ~/self-improving). Avoid sharing secrets/sensitive data in conversations or change the skill to redact or exclude private channels before saving. - Autonomous SOP mismatch: autonomous-operation-sop.md allows tasks like 'backup GitHub' and scanning for skill info. Backing up external services typically requires credentials and network access — the skill declares no creds. If you permit autonomous background tasks, explicitly constrain them and require approval for any network/external backups. - Verify filesystem impact: ensure your environment allows the agent to write only to intended paths and that those paths don't contain other sensitive data. Consider sandboxing the skill's workspace or adjusting paths to a controlled directory. - If you need higher assurance, ask the skill author to clarify: (1) whether auto-create truly runs without explicit user opt-in, (2) how autonomous SOP is invoked and whether it will perform network operations by default, and (3) how saved SKILL.md/log content is sanitized to avoid accidental leakage of secrets. Given the above gaps and consent/privacy implications, treat this skill as suspicious until you confirm or constrain its automatic behaviors.

Type: OpenClaw Skill Name: procedural-memory Version: 1.4.0 The skill implements a 'procedural memory' system that allows the agent to self-evolve by generating and saving new executable instructions (SKILL.md files) to its workspace based on conversation history. While intended for productivity, this creates a significant persistence vector for prompt injection, where malicious patterns could be 'learned' and permanently stored. Furthermore, the 'autonomous-operation-sop.md' file authorizes the agent to perform unsupervised tasks including 'script experiments' and broad file backups (e.g., 'E drive'), which presents a high risk of unintended autonomous actions or unauthorized data access.