ClawHub
Back to skill

Security audit

Weaviate

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only Weaviate helper whose external API key examples are purpose-aligned but worth using carefully with sensitive data.

Install is reasonable for Weaviate development. Before using the API-based module examples, confirm the data being indexed or queried is approved for the chosen provider and prefer local modules when external data transfer is not acceptable.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

In this markdown file, the example shows reading OPENAI_API_KEY from the environment and sending it as X-OpenAI-Api-Key in client headers. The description does not include any warning that the skill may access credentials and transmit them to external services, which is a missing user warning under the markdown criteria.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The examples instruct users to enable API-based modules such as OpenAI, Cohere, and generative services, which can transmit indexed content and queries to third-party providers, but they do not warn about external data transfer, privacy, retention, or compliance implications. In a production-ready skill, this omission can cause users to unknowingly send sensitive documents, prompts, or metadata off-system.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.