Agentic pentesting and human-on-the-loop controls: what changes now?

TL;DR: Agentic systems are changing pentesting by letting software replay user flows, mutate inputs, and preserve execution traces while human researchers retain accountability for decisions that carry operational or compliance risk, according to Terra. The governance shift is not automation replacing judgment but making judgment the control that determines whether agent execution can safely continue.

NHIMG editorial — based on content published by terra: The Future of Pentesting Is Human Judgment and Agent Execution

By the numbers:

• 71% of NHIs are not rotated within recommended time frames, increasing the risk of compromise over time.
• 80% of identity breaches involved compromised non-human identities such as service accounts and API keys.

Questions worth separating out

Q: How should security teams govern agentic pentesting tools in production-like environments?

A: Treat them as delegated systems with explicit scope, named ownership, and approval checkpoints.

Q: How do IAM and PAM teams support agentic pentesting safely?

A: They should issue dedicated test identities, limit privilege to the minimum required for the assessment objective, and log every context grant as if it were production access.

Q: What do security teams get wrong about automated compliance workflows?

A: They often assume the workflow itself is the control.

Practitioner guidance

• Define approval gates for agent execution Set explicit checkpoints for when an agent can continue, especially after it reaches production-like endpoints, authentication boundaries, or risky parameter changes.
• Treat offensive agents as scoped non-human identities Assign least-privilege access, named ownership, and revocation paths for testing systems that can operate inside authenticated workflows.
• Require replayable execution traces Capture the full request sequence, parameter mutations, and decision points so findings can be reproduced and reviewed later.

What's in the full article

terra's full article covers the operational detail this post intentionally leaves for the source:

• How TORCH separates ambient agents from on-demand co-pilot agents in active research workflows.
• The researcher review flow for execution traces, request mutations, and step-by-step validation.
• The operating model for deciding when an agent may continue versus when human accountability must intervene.
• The way the platform is positioned for continuous validation across deployments and code changes.

👉 Read terra's analysis of human judgment and agent execution in pentesting →

Agentic pentesting and human-on-the-loop controls: what changes now?

Explore further

View Full Forum →  |  NHI Foundation Course →