Slide 13 of 28
Part 2 — Vulnerability TypesSlide 13
Slide 13 · Types 4–6 — Privilege Escalation, Backdoors, Resource Exhaustion
Three more ways code execution exceeds its intended scope — the last two are the hardest to detect.
Type 4 — Privilege escalation via generated code

The agent's execution environment may include access to credentials, tokens, or capabilities that the agent's LLM-level permissions don't reflect. Generated code can exploit this gap — for example, reading a cloud metadata API endpoint (http://169.254.169.254/) to retrieve instance credentials, then using those credentials to call APIs the agent was never authorized to use at the application level.

This is particularly dangerous in cloud-hosted agent deployments where the execution environment runs with an IAM role that has broader permissions than the agent's application-level controls suggest.

Type 5 — Backdoor insertion in generated code

A coding agent asked to implement a feature, fix a bug, or generate boilerplate code may — if its input is manipulated — generate code that appears to fulfill the task while also containing hidden functionality: a hardcoded admin credential, a web shell endpoint, a scheduled task that phones home, or a dependency on a malicious package.

Why this is subtle: The generated code compiles. It passes basic tests. It does what it was asked. The backdoor is hidden in logic that only activates under specific conditions, or in a dependency that looks legitimate. Without code review, it deploys to production and stays there.

This is the agentic version of a software supply chain attack — but instead of a compromised package, the attack enters through the agent's code generation output itself.

Type 6 — Resource exhaustion

Code that recursively calls itself, spawns unbounded subprocesses, writes to disk in an infinite loop, or makes unlimited API calls can exhaust host resources — CPU, RAM, disk, or API quota — until services fail. An agent with no resource limits on its interpreter is capable of self-inflicted denial of service, whether from malicious input or from a naive implementation of a resource-intensive task.

Real pattern: Coding agents asked to "process all files" or "retry until successful" without explicit bounds have generated code that consumed available disk space or ran indefinitely — discovered only when the host became unresponsive.

← Back Part 3: Attack Scenarios →