ClawHub
Back to skill

Security audit

MetatextAI

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a coherent MetatextAI connector, but its setup path can trigger unverified remote install scripts without clear user approval.

Review the oo CLI installation path before installing. Prefer installing from OOMOL's official documentation with a versioned or verified artifact, and require explicit approval before any agent runs pipe-to-shell setup commands. For normal MetatextAI use, confirm write payloads before running create_policy or run_test_scan.

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 (2)

External Script Fetching

High
Category
Supply Chain
Confidence
96% confidence
Finding

The skill includes a one-line remote install pattern that pipes a downloaded script directly into a shell, which removes opportunities for integrity verification, review, or pinning to a trusted artifact. If the remote host, transport, or published script is compromised, a user or agent following this guidance could execute arbitrary code on the local system.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction to use this skill for ANY MetatextAI request is overly broad and can cause an agent to route all MetatextAI-related tasks through this skill without considering narrower, safer, or more appropriate alternatives. In an automated agent setting, broad routing language increases the chance of unintended invocation and can indirectly trigger state-changing operations if the downstream task is mis-scoped.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.