Bomb Dog Sniff

Security-first skill management for OpenClaw - like a bomb-sniffing dog for skills. Sniffs out malicious payloads (crypto stealers, keyloggers, reverse shells) before installation. Quarantine → Scan → Install only the safe ones.

This skill appears to be what it claims (a scanner + safe installer) but take the following precautions before installing or running it with access to your real skills directory: - Inspect the SKILL.md and code yourself (scan.js, safe-download.js, scripts/sniff.sh). The SKILL.md contained unicode control characters — open it in a raw text editor to verify nothing hides in rendering. - Run the scanner in a sandbox or container first (e.g., throwaway VM or ephemeral container) and point it at known-good targets to validate behavior. - Review safe-download.js: it invokes 'unzip' and 'npx clawhub' and will copy files into your OPENCLAW_SKILLS_DIR. Ensure these subprocess calls and their arguments are acceptable in your environment and not run as root. - Verify quarantine behavior: confirm the quarantine path, permissions, and automatic cleanup meet your policy. Consider changing quarantine to a directory you control. - Check that network downloads are limited to HTTPS and consider mirroring sources you trust rather than relying on arbitrary GitHub repos or clawhub via npx. - Prefer running the scanner (scan.js) only before automatic installs; use --dry-run and review JSON reports before allowing any auto-install. - If you are not comfortable auditing the code, prefer community-vetted scanners or obtain this package from an authoritative repository with a commit history and maintainer traceability. Given the prompt-injection indicator and the use of subprocesses that act on downloaded code, manual review or sandboxed execution is recommended before granting it access to your real skill installation directory.

Type: OpenClaw Skill Name: skill-bomb-dog-sniff Version: 0.1.0 The OpenClaw AgentSkills skill bundle 'bomb-dog-sniff' is a security scanner designed to detect malicious patterns in other skills. Its core components (`scan.js`, `safe-download.js`, `patterns.js`, `scripts/sniff.sh`) are all focused on this purpose. The skill implements robust security measures such as path sanitization, secure quarantine directories, download size/timeout limits, and symlink loop protection. While it interacts with the file system, network, and child processes, these actions are necessary for its stated function and are performed with security best practices. The presence of explicitly labeled 'test-malicious-skill' files (e.g., `test-malicious-skill/scripts/malicious.js`) demonstrates the scanner's detection capabilities rather than indicating malicious intent of the skill itself. The `SKILL.md` documentation is descriptive and does not contain prompt injection attempts against the AI agent.