ClawHub
Back to skill

Security audit

sop-dev-004-operaciones-sandbox

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Spanish SOP for changing OpenClaw sandbox modes, with operational risk but no hidden or unrelated behavior in the artifact.

Install only if you want a Spanish-language SOP for OpenClaw sandbox operations. Before following it, confirm the target environment, make or verify a backup of openclaw.json, understand that restarting the gateway may affect active sessions, and ensure the sandbox mode is restored as intended after the task.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill instructs changing a live configuration file and restarting the gateway service, but it does not explicitly warn the user that this alters isolation boundaries and can affect running agent behavior. In context, switching sandbox.mode to "all" or "off" changes execution safety posture, so omission of impact warnings increases the risk of accidental unsafe operation or production disruption.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The operational instructions and trigger descriptions are presented exclusively in Spanish, which may impose a language choice on users without offering an alternative or documenting the locale requirement. The file does not state that the skill is intended only for Spanish-speaking operators or provide a language-selection mechanism.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The manifest names the skill "sop-dev-004-operaciones-sandbox" and the provided context describes it as "SOP Canónico: sop-dev-004-operaciones-sandbox", suggesting a specific sandbox-operations SOP. However, the actual description field is only "Descripción de SOP: dev", which is materially broader and less specific than the skill identity and stated purpose context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.