ClawDefender - OpenClaw Security - Prompt injection, rogue skills etc

Security scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal attacks. Use when (1) installing new skills from ClawHub, (2) processing external input like emails, calendar events, Trello cards, or API responses, (3) validating URLs before fetching, (4) running security audits on your workspace. Protects agents from malicious content in untrusted data sources.

Install only if you want a local heuristic security helper that scans workspace skills/scripts and can assist with skill installation. Do not treat --check-url or --install as a complete safety boundary: --install installs first and scans afterward, and the URL allowlist is simple pattern matching. Review findings manually before acting on them, and only add HEARTBEAT or cron usage if you want persistent future behavior.

Type: OpenClaw Skill Name: clawdefender Version: 1.0.1 The skill bundle 'clawdefender' is a security tool designed to protect AI agents from various attacks, including prompt injection, command injection, SSRF, credential exfiltration, and path traversal. The `SKILL.md` clearly outlines its defensive purpose and instructs the agent to be cautious of flagged content. The `clawdefender.sh` script implements extensive detection patterns for malicious activities and performs audits, input validation, and safe skill installation. The `sanitize.sh` script acts as a wrapper for prompt injection detection. All observed behaviors are consistent with a legitimate security scanner and lack any evidence of intentional harmful actions by the skill itself.