OpenClaw Coding Agent Playbook

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only playbook for launching other coding agents; its powerful modes are visible and aligned with that purpose, but should be used carefully.

Install only if you are comfortable using this skill to launch other coding agents. Use temp clones or worktrees for reviews, keep tasks narrowly scoped, avoid exposing production secrets, and treat full-auto or bypassPermissions modes as high-trust options that require careful review of resulting changes.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly instructs use of `claude --permission-mode bypassPermissions`, which disables normal permission safeguards for an external coding agent. In a skill whose purpose is to delegate repository work, this materially increases the chance of unintended file modification, secret exposure, destructive commands, or execution of unreviewed actions without any warning, gating, or justification tied to a trusted sandbox.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal