Sentinel — Agent Security Layer

Runtime security layer for OpenClaw agents. Intercepts and scans all external input (emails, API responses, web content, chat messages, calendar events) for...

This skill is a set of local bash filters that scan stdin and stdout for injections and secrets and stores logs under ~/.sentinel. Before installing/using: (1) review and test the scripts on non-sensitive sample data; (2) be aware the canary tool can modify files you point it at (e.g., SOUL.md or other prompts) — back up those files first; (3) the premium rules require jq and an optional premium_patterns.json file (if absent the premium check is a no-op); (4) expect false positives (hex strings or common words may trigger crypto/secret heuristics) — tune thresholds/patterns in ~/.sentinel/config.sh or by editing the patterns; (5) there are no hidden network calls in the provided scripts, but always inspect any third-party premium patterns before placing them in ~/.sentinel. If you need the sentinel to be enforced platform-wide, note that this package does not automatically force inclusion — you must integrate the scripts into your agent pipeline yourself.

Type: OpenClaw Skill Name: sentinel-oleg Version: 1.0.5 Claw Sentinel is a comprehensive runtime security suite designed to protect OpenClaw agents from prompt injection, data exfiltration, and secret leakage. The bundle consists of Bash scripts (sentinel-input.sh, sentinel-output.sh) and a large library of regex patterns (patterns.json) that scan data in real-time across multiple languages (EN, RU, ZH, etc.). It includes sophisticated normalization techniques to counter obfuscation (e.g., stripping zero-width characters, de-leeting, and base64 decoding) and implements a canary token system (sentinel-canary.sh) to detect system prompt extraction. All logic is transparent, operates locally, and aligns strictly with its stated defensive purpose.