Memory Analyzer

Analyzes conversation history, extracts user preferences and feedback, updates memory files automatically.

This skill appears to do what it says: read session transcripts and update memory files. Before installing, consider the privacy implications — memory files can contain sensitive data (phone numbers, account IDs, etc.). Recommended precautions: 1) Inspect and sanitize existing sessions/ transcripts to remove PII you don't want persisted, 2) run the analyzer in a safe environment first and review its proposed changes before allowing automatic writes, 3) restrict filesystem permissions on MEMORY.md / USER.md / other memory files, 4) add explicit prompting or a review step to the SKILL.md (or modify analyzer.py) so updates require human approval, and 5) audit any memory files the skill creates for accidental secrets (API keys, tokens). If you need help adapting the skill to require manual approval or to redact PII automatically, I can suggest code changes.

Type: OpenClaw Skill Name: memory-analyzer Version: 1.0.0 The `analyzer.py` script and `SKILL.md` instructions are benign, performing only local text generation and printing without malicious intent or prompt injection. However, the `memory_analyzer_output.json` file, included in the skill bundle, contains sensitive personal and operational information such as a WhatsApp number, Telegram ID, internal script names, and details about API issues. While the provided Python code does not actively exfiltrate this data, its presence in the bundle constitutes an unintentional information disclosure risk, making the overall skill package suspicious due to this operational security oversight.