TL;DR: 90.3% of security-relevant facts were disclosed from hidden system prompts under Verno Labs's benchmark data set, versus 73.5% for promptfoo. Prompt secrecy needs fact-level scoring, because disclosure can leak identity, tool and internal-reference data.
Editorial analysis by NHI Mgmt Group, based on content published by Verno Labs: “VernoRed vs promptfoo on prompt extraction”.
By the numbers:
- VernoRed disclosed 90.3% of the security-relevant facts hidden in the targets' system prompts.
- promptfoo disclosed 73.5% of the security-relevant facts hidden in the targets' system prompts.
- VernoRed extracted 84% of the internal references, including emails, endpoints, configuration values and secrets.
Key questions
Q: Why do exact tool names matter in agent security?
A: Exact tool names matter because they are often the identifier needed to invoke, chain or impersonate a capability.
Q: What breaks when system prompts contain identity and tool data?
A: The boundary between policy and execution starts to collapse.
Q: How should security teams reduce prompt injection risk in AI agents?
A: Security teams should reduce prompt injection risk by constraining what enters the context window, limiting tool permissions, and separating untrusted retrieval content from privileged instructions.
Practitioner guidance
- Inventory prompt-bound security facts Catalogue which identity, scope, tool and internal-reference facts are stored in system prompts, then classify which of them are safe to disclose and which must remain outside the model boundary.
- Remove exact identifiers from hidden prompts Move tool names, endpoints, emails, configuration values and secrets into external policy, lookup or orchestration layers so the prompt no longer carries the information an attacker needs.
- Test prompt leakage by fact category Measure identity, rules, tools, tool details and internal references separately so you can see which disclosure class creates the most practical abuse risk.
Bottom line: Prompt extraction in AI agents is a disclosure problem, not a simple text-recovery problem.
Glossary terms: Prompt Extraction, System Prompt, Fact-Level Scoring, Tool Identifier Leakage
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
Prompt extraction is an identity and governance problem, not a model-parroting problem. When an agent discloses who it is, what it can do and what tools it knows about, the organisation has already leaked control-plane knowledge. That makes prompt content part of the identity boundary for agentic systems, especially when prompts encode scope, tool access and internal references. The practitioner conclusion is simple: if the prompt contains operational truth, it must be governed like policy.
A question worth separating out:
Q: How do teams tell whether prompt testing is actually meaningful?
A: Prompt testing is meaningful when it measures disclosure by fact category and by exact identifier, not by broad similarity alone. If identity facts, rules, tools and internal references are scored separately, teams can see where disclosure creates real abuse potential. A single aggregate score hides the controls that matter most.
👉 Read our full editorial: Prompt extraction benchmarks expose how AI agents leak security facts