subagent-architecture
Facilitates advanced orchestration of subagents with security isolation and collaboration patterns for robust multi-agent systems.
Install this skill
Security score
The subagent-architecture skill was audited on Feb 28, 2026 and we found 17 security issues across 3 threat categories, including 5 critical. Review the findings below before installing.
Categories Tested
Security Issues
Direct command execution function call
| 375 | ├─ Tools: exec (curl only) |
Direct command execution function call
| 945 | - ❌ No memory limits per spawn (subagent can consume unlimited RAM) |
Direct command execution function call
| 1039 | - Over-specify context in initial spawn (bloated prompts) |
Direct command execution function call
| 1445 | - Memory limits per spawn (prevent individual subagent memory leaks) |
Direct command execution function call
| 1446 | - API call quotas per spawn (prevent runaway costs) |
Direct command execution function call
| 1447 | - Disk space caps per spawn (prevent storage exhaustion) |
Template literal with variable interpolation in command context
| 282 | console.log(`Estimated: $${estimate.expected} (range: $${estimate.min}-$${estimate.max})`); |
Template literal with variable interpolation in command context
| 291 | console.log(`Quality: ${score.overall_score}/10 (${score.pass ? 'PASS' : 'FAIL'})`); |
Template literal with variable interpolation in command context
| 1200 | console.warn(`⚠️ Pattern has 65% success rate (13/20). Common failure: ${history.top_failure_mode}`) |
Template literal with variable interpolation in command context
| 1340 | task: `Implement skill-x per plan: ${plan.path}`, |
Template literal with variable interpolation in command context
| 1350 | task: `Review implementation: ${implementation.path}`, |
Template literal with variable interpolation in command context
| 1375 | message: `Security review request:\n${JSON.stringify(package)}\n\nFocus: Payment processing, SQL injection, input validation` |
Template literal with variable interpolation in command context
| 1627 | console.log(`${type}: ${(successRate*100).toFixed(1)}% success, $${avgCost.toFixed(2)} avg cost, ${avgValue.toFixed(1)} avg value`); |
Webhook reference - potential data exfiltration
| 16 | - name: Discord webhook (peer review flow) |
Webhook reference - potential data exfiltration
| 18 | notes: "Only needed if using the federated peer-review pattern. User must supply their own webhook URL manually. No token is stored or auto-configured by this skill." |
Webhook reference - potential data exfiltration
| 65 | - **Discord webhooks** — Only used in the federated peer-review pattern. You supply your own token manually. This skill does not store or transmit credentials. |
Access to .env file
| 247 | > const SKILL_DIR = path.join(process.env.OPENCLAW_WORKSPACE || process.cwd(), 'skills', 'subagent-architecture'); |