Sensitive Info Protection

Sensitive information real-time protection skill that automatically detects, alerts, and handles sensitive data in user interactions. Supports custom detecti...

This skill appears coherent and implements what it describes. Before installing or enabling it, consider: (1) it will read any config file path you provide (via load_config or CLI) so avoid pointing it at files you don't want parsed; (2) its detection is regex-based — review and test default_rules.json and any custom rules to avoid false positives/overblocking; (3) assets/sensitive-interaction.js injects UI buttons into a webchat DOM — review that script if you plan to run it in a browser to ensure its behavior matches your expectations (it manipulates input fields and triggers send actions); (4) no network exfiltration or credential usage is present in the code, but always review custom rule sources before importing dynamic rules. If you want extra assurance, run the provided tests (tests/test_basic.py) in a sandboxed environment first.

Type: OpenClaw Skill Name: sensitive-info-protection Version: 1.0.0 The skill is a legitimate utility designed to detect and prevent the accidental exposure of sensitive information such as API keys, credit card numbers, and PII. The Python implementation (detector.py, models.py) uses standard regex-based scanning and lacks any network, file exfiltration, or shell execution capabilities. The included JavaScript (sensitive-interaction.js) provides a functional UI enhancement for the OpenClaw interface, allowing users to confirm, edit, or cancel messages containing sensitive data; while it automates DOM interactions, it does not exfiltrate data or exhibit malicious intent.