OpenClaw Browser Relay Reliability

Harden OpenClaw browser extension relay behavior by eliminating blank-target tab churn, fixing download behavior forwarding, and standardizing download paths.

This appears to be a documentation-style troubleshooting skill for fixing OpenClaw extension-relay download and tab behavior, but there are small inconsistencies you should clarify before installing: - Confirm why 'rg' (ripgrep) is declared required. The SKILL.md never references running searches; if the skill expects to search code, ask the author for the exact commands and whether the agent will access your repository/workspace. - The SKILL.md lists specific source file paths as 'proof points' but no code is bundled. If you expect the skill to modify or verify those files automatically, request a concrete install or run plan (commands, file edits, or an automated patch). Otherwise treat this as a manual checklist only. - Because the skill is instruction-only, it cannot itself execute code from a remote URL, but an agent following the instructions could be directed (later) to edit files or run tools in your environment. Only enable it in environments where you trust the operator and where any repo referenced is safe to inspect. If you need to proceed: ask the skill author for (a) the exact intended runtime steps (what the agent will search or modify), (b) whether 'rg' is actually needed and how it will be used, and (c) a link to the repository or changelist that implements the hardening so you can review changes before they are applied. If you cannot get that, treat the skill as low-value documentation and avoid giving it broad agent permissions or running it autonomously on sensitive systems.

Type: OpenClaw Skill Name: openclaw-browser-relay-reliability Version: 0.1.0 The skill bundle contains metadata and documentation (SKILL.md) focused on improving the reliability of a browser extension relay. The stated goals—standardizing download paths to '~/Downloads/OpenClaw' and fixing tab creation logic—are consistent with legitimate browser automation hardening, and no malicious instructions, exfiltration logic, or obfuscated code were found in the provided files (_meta.json, SKILL.md).