ClawHub
Back to skill

Security audit

speak

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward text-to-speech wrapper for OpenClaw Talk with disclosed local command use and no persistence or hidden data access.

Install only if you want an assistant to speak selected text through the device speaker using your configured OpenClaw Talk provider. Do not use it for secrets, credentials, private prompts, or sensitive content unless you trust that provider path.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill invokes shell-capable components and uses environment configuration, but it does not declare any explicit tool scope such as permissions or allowed-tools. That mismatch weakens policy enforcement and reviewability, making it easier for the skill to run commands or access environment-dependent resources without clear constraints.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/run.py (reported line 38)May include surrounding context.

python
try:
    proc = subprocess.run(
        [
            openclaw,
            "gateway",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The script transmits all provided speech text to the external openclaw gateway call talk.speak service, but the file contains no user-facing disclosure or consent mechanism. In a voice/speech skill, users may reasonably assume local playback; sending potentially sensitive text off-device can expose secrets, personal data, or internal prompts to another system.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/run.py (reported line 107)May include surrounding context.

python
command.append("-")


player = subprocess.run(
    command,
    input=audio,
)