Spawn Subagent

AdvisoryAudited by VirusTotal on Apr 2, 2026.

Overview

Type: OpenClaw Skill Name: spawn-subagent Version: 1.0.1 The skill bundle provides documentation and usage patterns for a 'subagent spawning' capability, intended to delegate long-running tasks to isolated sessions. The instructions in SKILL.md and the deprecation notice in DEPRECATED.md focus on operational efficiency, error handling, and cost management, using legitimate examples such as file summarization and calendar/email management via CLI tools. No evidence of malicious intent, data exfiltration, or harmful prompt injection was identified.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

A subagent can continue working while the main session moves on, which may consume resources or perform delegated actions until it completes or times out.

Why it was flagged

The skill's core function is to start a separate subagent for delegated work. This is disclosed and bounded by recommended timeouts, so it is a usage note rather than a concern.

Skill content
sessions_spawn(... mode="run", runtime="subagent", runTimeoutSeconds=300)
Recommendation

Use subagents only for clearly scoped tasks, always include a timeout, and avoid delegating sensitive or irreversible actions unless the user explicitly asked for them.

What this means

Sensitive paths, environment variable names, API endpoints, or generated outputs could be shared with the spawned subagent and written to disk.

Why it was flagged

The instructions explicitly pass task context, locations, and outputs between the main agent and a subagent. This is expected for delegation, but users should notice the data boundary.

Skill content
Where inputs are — file paths, env vars, API endpoints ... What to output — exact format and save location
Recommendation

Pass only the minimum context needed, avoid including secrets in the task description, and write outputs to scoped temporary locations.

What this means

If used as shown, a subagent may read email and calendar data for the selected account.

Why it was flagged

One example delegates calendar and email reads through an account-scoped CLI. That is coherent for a daily briefing workflow, but it uses delegated account access.

Skill content
GOG_ACCOUNT=owner@company.com gog calendar events ... gog gmail search 'is:unread newer_than:1d'
Recommendation

Confirm the intended account and query scope before using account-backed examples, and require explicit approval for any sending, deletion, or other account mutation.

What this means

Failure logs may preserve sensitive filenames, task details, or error output for later sessions.

Why it was flagged

The failure-handling instructions create a persistent local record. This is useful for troubleshooting, but persistent logs can retain task context.

Skill content
Log the failure: append to `.learnings/ERRORS.md`.
Recommendation

Do not log secrets or sensitive content, and periodically review or delete `.learnings/ERRORS.md` if it may contain private data.