ClawHub
Back to skill

Security audit

BailingHub Agent Governance Executor

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed outbound executor that connects OpenClaw to a user-configured BailingHub control plane, with sensitive behavior documented and bounded.

Install only if you intend this machine to process jobs from the specified BailingHub target. Use a target-scoped token, start with BAILING_RUN_ONCE=1 on non-sensitive test data, run under a dedicated non-root account, and keep OPENCLAW_FORWARD_ENV limited to the exact variables OpenClaw needs.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding

The skill explicitly requires environment variables and outbound network access, and instructs the operator to run a Node-based executor that polls a remote control plane, yet it declares no explicit tool scope or permissions metadata. This creates a policy/visibility gap: reviewers and runtime controls may not realize the skill can access secrets and communicate externally, increasing the chance of overprivileged deployment or unsafe approval.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 77)May include surrounding context.

md
- A working, non-interactive OpenClaw agent.
- A stable executor id approved by the user, or permission to use the hostname.

Do not guess missing values. Never ask the user to paste the executor token into chat. Ask them to place it in a local secret store or hidden environment input.

## Connect

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
scripts/bailinghub-openclaw-executor.mjs:377

Environment variable access combined with network send.

Critical
Code
suspicious.env_credential_access
Location
scripts/bailinghub-openclaw-executor.mjs:53