Security audit

claw-shell

Security checks for vulnerabilities and agentic risk

Overview

This skill is a shell-command tool, but its safety controls do not reliably keep execution inside the declared tmux session or require confirmation for risky commands.

Install only if you explicitly want an agent-facing raw shell tool. Treat every command as potentially running with your local account permissions, avoid exposing it to untrusted prompts or content, and prefer a version that uses argument-array process execution plus real per-command approval for destructive operations.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: handler.js:10
Finding: Shell Command Injection and Bypassable Destructive-Command Controls
Content: View full analysis
lower.includes(k)); } // MAIN ENTRYPOINT // OpenClaw will call this function when using the skill tool async function claw_shell_run(input) { const { command } = input; if (!command || typeof command !== "string") { return { error: "command is required" }; } if (isDangerous(command)) { return { error: "dangerous_command", message: `Command looks dangerous. Ask the user for explicit approval before running: ${command}` }; } ``` ### Technical Analysis The `command` value is controlled through the Skill input and is interpolated directly into a string passed to `execSync`. Because `execSync` executes the constructed string through a system shell, shell syntax in the input is interpreted before `tmux` receives the intended command. The implementation only escapes double-quote characters: ```js const escaped = cmd.replace(/"/g, '\\"'); ``` This does not neutralize shell command-substitution constructs such as `$()` or backticks. Shell expansion can therefore execute an injected command in the process used to invoke `tmux`, outside the documented `claw` tmux session. Backslash and quote combinations may also interfere with the intended quoting boundary. The `isDangerous` control does not adequately mitigate thi ...[truncated 2324 chars]
Remediation: View remediation

SkillSpector

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

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill executes arbitrary shell commands provided through input by sending them into a persistent tmux shell session, but only applies a weak keyword blacklist and provides no enforced user confirmation or clear disclosure before execution. This allows many dangerous commands to run unimpeded, including destructive or data-exfiltrating commands that bypass the blacklist, and the persistent session increases the chance of compounded impact across multiple invocations.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: handler.js:5