Join our Newsletter — 33% off our NHI Course

Why does 11% of agentic work stay in prompts?

 

(@nhi-mgmt-group)
Member Moderator
Joined: 2 years ago
Posts: 20225
Topic starter  

TL;DR: Prompt and output filtering covers only a small slice of agent behaviour, according to Manifold Security, because the article says prompts and outputs make up just 11% of activity. Runtime governance has to follow the agent into tool use, endpoint visibility and action attribution.

Editorial analysis by NHI Mgmt Group, based on content published by Manifold Security: “Joe Sullivan Joins Manifold's Board”.

By the numbers:

  • Prompts and outputs are 11% of what an agent does, while the other 89% are actions, including 51% tool calls.

Key questions

Q: Why do AI agents increase identity risk even when the login succeeds?

A: A successful login only proves that the agent reached the system.

Q: How should security teams govern agentic work across endpoints and cloud tools?

A: They should govern the full action path, starting at the endpoint where the agent launches tools and continuing through every system it can touch.

Q: Why do prompt filters fail as the main control for AI agents?

A: Prompt filters only address the input layer, while most business risk appears after the agent has access to tools and data.

Practitioner guidance

  • Map agent actions, not just prompts Inventory where agents can open files, call tools, move through browsers and execute desktop actions under employee identity.
  • Reclassify agent sessions as privileged events Treat agent logins as delegated access that may require stronger approval, tighter scope and closer monitoring than ordinary interactive use.
  • Instrument the endpoint as a control point Extend monitoring to the machine where the agent runs, because that is where browser actions, desktop operations and cloud sandbox activity can be observed together.

Bottom line: Agents now create risk through actions, not only through prompts, so security controls have to move to the execution layer.

Glossary terms: Agentic Workforce, Runtime Governance, Delegated Identity, Security Control Plane

Explore further

View Full Forum →  |  NHI Foundation Course →  |  Our Services →  |  Read the full analysis →


This topic was modified 1 week ago by NHI Mgmt Group

   
Quote
(@mr-nhi)
Member Moderator
Joined: 6 months ago
Posts: 20715
 

Prompt filtering is now a partial control, not a primary control: The article correctly shows that text inspection only covers a narrow slice of agentic behaviour. Once agents can act through browsers, desktops and cloud tools, the more important question is what they are authorised to do after the prompt ends. Security teams should stop treating prompt safety as the main boundary and start treating it as one input to a wider runtime governance model.

A few things that frame the scale:

  • AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.

A question worth separating out:

Q: Should organisations treat agent activity differently from ordinary user activity?

A: Yes. Agent activity should be treated as delegated, high-speed identity activity because the software can combine access, automation and tool use in ways that ordinary user sessions do not. That difference justifies stronger observation, narrower scope and clearer approval boundaries.

👉 Read our full editorial: Agentic workforce security shifts from prompt filtering to runtime control


This post was modified 1 week ago by NHI Mgmt Group

   
ReplyQuote
Share:

Free weekly newsletter

Subscribe to the NHI & AI Identity Journal

The latest on NHI and Agentic AI security – articles, research, breaches, news and events every week.

Bonus 33% off our NHI Course when you subscribe.