Subagent Isolation Guard

固化子代理物理隔离与语义路由旁路。防止跨代理上下文污染及由于语义路由导致的子代理切模/重置问题。

This instruction-only skill is coherent for hardening subagent isolation, but it asks you to add a routing bypass and require session IDs to contain ':subagent:'. Before implementing: (1) perform a code review of semantic-webhook-server.py changes and restrict who can edit it and AGENTS.md; (2) avoid relying on a plain string marker — require authenticated, signed, or unforgeable session tokens (not just a prefix) so attackers cannot spoof ':subagent:'; (3) add logging, monitoring, and audits for all bypassed requests; (4) test thoroughly in a staging environment to ensure the bypass doesn't let untrusted inputs evade policy or model-safety checks; (5) consider safer alternatives (e.g., mutual TLS, signed JWT session claims, or an allowlist tied to agent identities) if you need robust isolation. If you cannot enforce these controls, treat deploying this bypass as high risk.

Type: OpenClaw Skill Name: subagent-isolation-guard Version: 1.0.0 The skill bundle contains architectural guidelines and documentation for implementing subagent isolation and routing bypass within the OpenClaw framework. It focuses on preventing context pollution and session resets by recommending separate workspaces and specific session tagging, with no executable code, malicious instructions, or data exfiltration risks identified in SKILL.md or _meta.json.