OpenClaw Coding Agent Workflows

• Outcome: Review
• Latest audit: May 29, 2026, 9:34 PM
• Version:
  1.0.0

Overview

This instruction-only skill is coherent for delegating coding work, but it normalizes high-autonomy agent modes with reduced approval safeguards.

Install only if you intentionally want OpenClaw to orchestrate other coding agents for repository work. Use isolated worktrees or temp clones, review diffs before merging, avoid sensitive repositories or secrets when using delegated agents, and treat `--full-auto` and `--permission-mode bypassPermissions` as elevated modes that reduce normal approval safeguards.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill explicitly instructs users to launch Claude Code with `--permission-mode bypassPermissions`, which weakens or removes interactive safety checks for subprocess actions. In a skill whose purpose is to delegate coding tasks to autonomous agents, this increases the chance of unintended file changes, secret exposure, destructive commands, or unsafe network/git operations, especially because the documentation presents this mode as a normal execution pattern rather than a tightly controlled exception.

VirusTotal

66/66 vendors flagged this skill as clean.