ClawHub
Back to skill

Security audit

Baixiao AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Baixiao/OOMOL connector, but its first-time setup includes direct remote installer execution that users should review before installing.

Review the first-time setup before installing. Prefer installing the oo CLI through a verified package or by downloading and inspecting the installer rather than piping a remote script directly into a shell. Also confirm any write action, dynamic call_tool use, personal knowledge-base search, or PDF retrieval that may expose account data or consume credits.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The first-time setup instructions include piping a remote script directly into bash, which is a classic unsafe installation pattern. If the remote host, transport, or delivered script is compromised, arbitrary code would execute immediately on the user's machine with the user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 74)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill metadata says to use this skill for ANY Baixiao AI request and instead of calling the API directly, which creates an overly broad routing rule. That can cause the agent to invoke this skill for a wide range of user intents without sufficiently checking whether the user actually wants this connector path, increasing the chance of unintended data access, writes, or cost-incurring actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

Several action descriptions explicitly prioritize Chinese-language scholarship, Chinese government policy, Hong Kong funding data, and ideological text collections, including xi_thought_search. The file does not state that these locale/content constraints are optional, user-selected, or justified as a region-specific skill, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.