APromptRiskDBThreat intelligence atlas
AI Security Technique

Call Chains - AI Security Technique

Adversaries may extract call chains from AI agent configurations, which can reveal potentially targets for remote code execution (RCE) or other vulnerabilities. Vulnerable call chains often connect user inputs or LLM outputs to an execution sink (e.g. exec, eval, os.popen). The vulnerabilities may be later exploited via LLM Prompt Injection. Adversaries may systematically identify potentia...

AI Security Techniquedemonstrated

Record summary

A quick snapshot of what this page covers.

Tactics0Attacker goals connected to this method.
Mitigations0Defenses that may help against this attack.
AI risks12Research-backed risks connected to this topic.

Attack context

How this AI attack works in practice.

Adversaries may extract call chains from AI agent configurations, which can reveal potentially targets for remote code execution (RCE) or other vulnerabilities. Vulnerable call chains often connect user inputs or LLM outputs to an execution sink (e.g. exec, eval, os.popen). The vulnerabilities may be later exploited via LLM Prompt Injection.

Adversaries may systematically identify potentially vulnerable call chains present in LLM frameworks, then scan for applications that are configured to use these call chains for targeting [1].

References

  1. [1] https://arxiv.org/abs/2309.02926
ATLAS ID
AML.T0084.003
Priority score
90
Maturity: demonstrated

Mitigations

Defenses that may help against this attack.

No connected defenses. No defense is connected to this attack in the current data.

Case studies

Examples from public reports and exercises.

LLMSmith: RCE Vulnerabilities in LLM-Integrated Applications

exercise
Date2025-02-27

Researchers identified 20 remote code execution (RCE) vulnerabilities across 11 different LLM frameworks. They discovered applications deployed on the public internet built using these LLM frameworks and demonstrated the RCE vulnerabilities could be exploited using prompt injection.

The 11 LLM frameworks the researchers evaluated were: LangChain, LlamaIndex, Pandas-ai, Langflow, Pandas-llm, Auto-GPT, Griptape, Lagent, MetaGPT, vanna, and langroid.

Source

Where this page information comes from.