Initial Access

Type: tactic

Description: Get your text into the LLM prompt

Version: 0.1.0

Created At: 2025-03-04 10:27:40 -0500

Last Modified At: 2025-03-04 10:27:40 -0500

Tactic Order: 3

External References

  • <-- RAG Poisoning (technique): An adversary can gain initial access by injecting malicious content into a publicly available data source indexed by RAG.
  • <-- ML Supply Chain Compromise (technique): Compromising machine learning supply chains to gain unauthorized access or introduce malicious components.
  • <-- Evade ML Model (technique): Bypassing or evading machine learning models used for security or detection to gain unauthorized access.
  • <-- Retrieval Content Crafting (technique): An adversary can target a specific user prompt by crafting content that would be surfaced by a RAG system to respond to that query.
  • <-- User Manipulation (technique): An adversary can indirectly inject malicious content into a thread by manipulating a user to do it unwittingly.
  • <-- Retrieval Tool Poisoning (technique): An adversary can indirectly inject malicious content into a thread by contaminating data accessible to the AI system via an invocable retrival tool.
  • <-- Phishing (technique): Using phishing techniques to gain unauthorized access to systems or machine learning environments by tricking individuals into revealing sensitive information.
  • <-- Compromised User (technique): An adversary can directly access the AI system by using a compromised user account.
  • <-- Guest User Abuse (technique): An adversary could leverage a guest user account as a foothold into the target environment.
  • <-- Valid Accounts (technique): Using valid accounts to gain initial access to systems or machine learning environments.
  • <-- Web Poisoning (technique): An adversary can indirectly inject malicious content into a thread by hiding it in a public website that the AI system might search for and read.
  • <-- Exploit Public-Facing Application (technique): Exploiting vulnerabilities in public-facing applications to gain unauthorized access to systems or data.