System Prompt Leakage

← AI/ML (OWASP LLM/GenAI Top 10)

system_prompt_leakage   EASY

Description

System prompt (with a fake secret) is extractable via the chat.

How it works

The assistant has no protection around its system prompt, which contains a hardcoded internal secret. A simple request makes it echo the full system prompt, and the secret with it, back to the user.

How to exercise it. DVMA is the harness - open this module from the home index and tap the demo action. The screen ships the malicious input and simulates the attacker (e.g. the companion app, crafted intent, or scanned payload) in-process, and the evidence panel prints the proof. The Tools (optional) and Attack inputs below are only needed to reproduce the exploit end-to-end on a real device.

Exploit steps

1. Set up. Build DVMA with a flavor that enables the AI/ML (OWASP LLM/GenAI Top 10) category (e.g. --dart-define-from-file=config/flavors/dev.json) and run on an emulator/simulator you control. The demo needs no external tooling; for the optional on-device reproduction the relevant tools are: garak, promptfoo.
2. Locate the target. From the home index, open System Prompt Leakage (system_prompt_leakage). The How it works section above describes this module’s specific weakness; the screen states the intended-secure behavior and exposes the vulnerable action.
3. Exploit. Send the crafted prompt / poisoned content to the in-app assistant and confirm the model obeys it - leaked system prompt/secret, an unconfirmed tool call, or attacker-controlled output.
4. Observe the evidence. Trigger the vulnerable action and read the evidence panel - it prints the concrete proof (leaked value, accepted replay, executed payload, or unauthorized result).
5. Contrast with the secure path. Run the module’s secure/hardened action (where provided) and confirm the same attack is rejected - this is what a correct implementation should do.

Tools (optional)

• garak
• promptfoo

garak / promptfoo / MCP scanner test the LLM or MCP endpoint behind the app, not the app binary. Point them at the backend model API (find it with mitmproxy / Burp Suite) or a local on-device model server; the in-app demo already exercises the same prompt path.

Attack inputs

Payloads/artifacts you author for the on-device attack. The demo already ships and simulates these in-process (e.g. the malicious companion app / crafted intent is emulated inside the screen), so you only need to craft them to reproduce the exploit on a real device:

• crafted prompt