recursive-spawn
What this skill does
Enables an Openclaw agent to spawn sub-agents (child Openclaw instances) when a task is too large, complex, or parallel to handle alone. It is a utility for task delegation and parallel execution.
github/leoyeai - Data Exposure - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=recursive-spawnAssessments (2)
Data Exposure
Data Exposure via local-llm-review
scripts/spawn_openclaw.py
The script mentions that 'progress_so_far is sent to the provider API and visible to the child agent - sanitize snapshots and strip secrets before spawning.' This indicates that if not properly saniFilesystem Access
Filesystem Access via local-llm-review
scripts/spawn_openclaw.py
The script notes that 'passing file-access tools to children grants them read/write access to arbitrary paths - only pass tools you trust.' This highlights a potential risk if untrusted tools are paBadge
Add the Anomity scan badge for recursive-spawn to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of recursive-spawn? Report an issue or request a rescan.
