Clawhub Publish

Scans SKILL.md files with 7 regex layers to block prompt injection, reverse shells, memory tampering, encoding evasion, and trust abuse before LLM processing.

This skill is internally consistent with being a local SKILL.md sanitizer: it has no network calls, no required credentials, and a single Python file using only standard library modules. Before installing or running it: 1) verify the source (registry metadata shows 'source: unknown' and no homepage in the registry entry—prefer a published repository or checksum), 2) inspect the full python file yourself (or run it in a sandbox) to confirm there are no hidden network calls in parts of the file you haven't read (the provided file is truncated in the listing), 3) if you enable semantic analysis, understand that requires a local Ollama instance and local model usage, and 4) be aware the SKILL.md intentionally includes injection examples (they will trigger the scanner). If you need higher assurance, obtain the code from an authoritative repo, verify a signed release or checksum, and run the built-in test suite locally.

Type: OpenClaw Skill Name: skill-sanitizer Version: 2.1.1 The OpenClaw AgentSkills skill bundle 'skill-sanitizer' is designed to detect malicious patterns in other skills, not to perform malicious actions itself. The `SKILL.md` clearly outlines the types of attacks it aims to prevent (e.g., prompt injection, reverse shells, memory tampering) and provides examples of such malicious content as illustrations for detection, not as instructions for the agent. The `skill_sanitizer.py` code implements robust, local, and dependency-free detection logic using regex, unicode normalization, and base64 decoding to identify harmful patterns. There is no evidence of data exfiltration, persistence mechanisms, unauthorized remote control, or any other malicious intent within the sanitizer's own code or instructions.