Matz Swarm

Orchestrate OpenClaw Agent Swarm workflows for multi-project coding automation with Obsidian task intake, Claude coding, Codex review, GitLab MR flow, merge+...

What you should consider before installing: - Read the scripts top-to-bottom. This skill will create worktrees, run tmux sessions, change files (tasks.json, registry.json, Obsidian notes/context.md), push branches, create/merge MRs, and delete worktrees/logs. Back up repositories and notes before running. - Credentials: the scripts expect authenticated CLIs (claude/codex OAuth config, glab/gh auth, and openclaw or webhook config). The skill metadata does not declare these env vars — you must ensure tokens are scoped and stored safely (use least privilege tokens for the Git provider and notification system). - Dangerous CLI flags: the code deliberately uses flags like --dangerously-skip-permissions and --dangerously-bypass-approvals-and-sandbox to bypass approval/trust dialogs for automation. If you plan to use this, remove or audit those flags so automated agents cannot bypass safety sandboxes. - Automatic merges: the SKILL.md maps simple user intents (e.g., user replies "merge") to immediate merge-and-sync actions without confirmation. If you need human review, modify the Intent→Action mapping or disable autonomous invocation/require explicit confirmations for merges. - Testing: run the system in an isolated test account/repo first. Configure cron disabled until you have verified behavior. Limit notification targets (e.g., set notifyMethod to none) until you trust behavior. - Minimal changes: if you want the orchestration but safer defaults, consider edits: remove 'dangerous' CLI flags, require manual approval before merging, add explicit declared required env vars in the skill metadata, and tighten the notification delivery paths. If you want, I can produce a concise list of edits to the scripts to harden default behavior (disable dangerous flags, add confirmation prompts for merging, and declare expected env vars).

Type: OpenClaw Skill Name: matz-swarm Version: 1.1.1 The bundle describes a complex 'Agent Swarm' orchestrator that automates coding tasks using LLMs and Git. While the intent appears to be a legitimate productivity tool, it implements extremely high-risk security patterns, including explicitly disabling AI safety sandboxes and permission prompts (e.g., '--dangerously-skip-permissions' for Claude and '--dangerously-bypass-approvals-and-sandbox' for Codex in config.sh). It also performs automated 'npm install' on AI-generated code and uses cron jobs to execute shell scripts based on the contents of local Markdown files (scan-obsidian.sh), creating a significant attack surface for RCE via prompt injection or local file manipulation. No clear evidence of intentional malice or data exfiltration was found, but the design is inherently insecure.