domains / families / security / testing-for-system-prompt-leakage

testing-for-system-prompt-leakage

separate

Extracts LLM system prompts using direct requests, jailbreak/instruction-override

When to use

• During an LLM application penetration test or red-team engagement (OWASP LLM07 coverage).
• When validating that no secrets, credentials, or authorization logic live in the system prompt.
• When verifying that guardrails block prompt-extraction attempts.
• When building a regression suite that fails the build if a new prompt leaks.
• When assessing multi-agent or RAG apps where the preamble defines tool routing.

When not to use

• testing systems without written authorization

Skill page

Source