ClawHub
Back to skill

Security audit

RAG Production Engineering

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only RAG engineering guide whose behavior matches its stated purpose and does not request dangerous access or hidden execution.

This skill appears safe to install as a RAG engineering reference. Users should understand that it may steer broad RAG-related requests into its methodology, and any external service choices, logging, access-control design, or production changes it recommends should still be reviewed before implementation.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The quick-start instruction uses a very broad activation phrase ('I need to build a RAG system for [your use case]') without defining scope, boundaries, or consent conditions. This can cause the skill to activate in loosely related conversations and steer the agent into detailed methodology or recommendations when the user did not explicitly request this specific skill, creating prompt-routing and unintended-behavior risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill defines very broad natural-language triggers such as 'Set up a RAG system', 'Optimize retrieval', and 'Review my RAG architecture', which overlap with ordinary user support phrasing and can cause unintended invocation. In an agent ecosystem, ambiguous activation can route unrelated conversations into this skill, leading to scope confusion, unintended processing of sensitive content, or bypass of more appropriate specialized skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.