ClawHub
Back to skill

Security audit

HaiGuanJia

Security checks for vulnerabilities and agentic risk

Overview

The HaiGuanJia workflow includes approval safeguards, but its software setup can execute unchecked downloads and introduce changes to other agents.

Review and install a verified CLI release before use. Consider disabling its startup skill synchronization with OO_SKILLS_SYNC_DISABLED=1, as documented in the [CLI reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). Keep write/delete approvals, check charges, and share only authorized documents and tracking data. The external installers and hosted connector implementation remain unverified; no malicious behavior was established.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The supplied chunk performs remote software installation rather than HaiGuanJia data operations. It provides no evidence that installing the Oomol CLI is a supporting dependency for the declared purpose. The downloaded script's contents are not supplied, so its further effects cannot be determined.

Content

No source excerpt is available for this finding.

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The setup command pipes a mutable remote script directly into Bash without inspecting it or verifying a pinned version, signature, or independently trusted digest; the PowerShell alternative has the same problem. Compromise of the distribution endpoint could execute arbitrary code with the agent's local privileges, potentially exposing local credentials and files. Conditional execution and HTTPS reduce exposure but do not establish the integrity of the script.

Content

Scanner excerpt · SKILL.md (reported line 130)May include surrounding context.

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 151)May include surrounding context.

md
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.

- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.

## Resources