Openclaw Egress

Network data loss prevention for agent workspaces. Scans skills and files for outbound URLs, data exfiltration endpoints, suspicious domains, and network function calls. Maps every external connection. Free alert layer — upgrade to openclaw-egress-pro for blocking, quarantine, and URL allowlists.

This skill largely does what it says — scanning for outbound URLs and network calls — but the bundled script contains code paths for saving an allowlist and for quarantining/modifying skills (renaming directories, inserting block comments). The SKILL.md and README emphasize 'alert-only' for the free version yet the code includes modification capabilities; source/homepage are not provided. Before installing or running: (1) review the full scripts (search for rename/move, os.remove, shutil.move, write/open calls that change other directories), (2) run scans on a copy or a non-production workspace first, (3) back up your workspace/skills, (4) prefer running with --skills-only and in read-only mode if available, and (5) avoid granting broad write access if you don’t trust the source. If you need absolute assurance, ask the publisher for a provenance URL or a signed release and/or run the script in an isolated container or VM.

Type: OpenClaw Skill Name: openclaw-egress Version: 1.0.2 This skill is designed as a Network DLP tool, which is a security-focused purpose. However, it possesses high-risk capabilities, including reading all files in the workspace, modifying code files by commenting out lines, and disabling other skills by renaming their directories. While these actions are intended for defensive purposes (blocking exfiltration, quarantining compromised skills), the power to alter code and disable components within the agent's workspace constitutes a significant capability that, if misused or buggy, could lead to denial of service or unintended code changes. The `scripts/egress.py` file contains the logic for these modifications, particularly in the `_block_lines`, `cmd_block`, `cmd_quarantine`, and `cmdtect` functions. The `SKILL.md` and `README.md` files are clean and do not contain prompt injection attempts.