Notifications
Clear all
Topic starter
06/09/2026 9:34 am
TL;DR: AI SOC agents can rotate credentials and trigger tools, but that autonomy turns secrets handling into the core control problem because API tokens, OAuth credentials, and service accounts can leak through prompts, logs, and external systems, according to Crogl. The practical issue is not whether an agent can see a secret, but whether security can govern who or what can trigger its use.
NHIMG editorial — based on content published by Crogl: Do Your Agents Know Your Secrets?
By the numbers:
- When AWS credentials are exposed publicly, attackers attempt access within an average of 17 minutes, and as quickly as 9 minutes in some cases.
- 64% of valid secrets leaked in 2022 are still valid and exploitable today, proving that detection alone is not enough without automated revocation.
- AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers.
Questions worth separating out
Q: What breaks when AI agents keep standing credentials?
A: The access model breaks because the agent can continue acting after the human has moved on, the workflow has shifted, or the original approval is no longer relevant.
Q: Why do AI agents increase secrets risk even when prompts do not expose credentials?
A: Because the risk shifts from visibility to invocation.
Q: How can security teams tell whether agent permissions are too broad?
A: The clearest signal is whether the agent can still complete its job after permissions are reduced in a sandbox.
Practitioner guidance
- Map agent-to-tool authority paths Inventory every tool, API, and workflow an agent can trigger, then document which credential or delegated identity executes each action.
- Separate model intent from credential use Design architectures so the LLM can request an action without directly receiving secrets, tokens, or long-lived credentials.
- Scope agent privileges to task boundaries Replace broad, persistent access with task-scoped permissions that match the smallest realistic work unit.
What's in the full article
Crogl's full blog covers the operational detail this post intentionally leaves for the source:
- The article’s architecture pattern for keeping secrets out of prompts while still allowing controlled tool execution.
- Crogl's explanation of how role-based controls scope agent actions inside a controlled execution layer.
- The distinction between system-required exposure and user-driven disclosure, which matters for governance decisions.
- The audit-trail and attribution model used when every agent action must remain traceable.
👉 Read Crogl's analysis of AI agents, secrets handling, and autonomous execution →
AI agent secrets handling: what it means for IAM teams?
Explore further
06/09/2026 9:34 am
Autonomous agents turn secrets governance into action governance. The important shift is not that agents may see credentials, but that they can be asked to use them at runtime. That means identity programmes must govern invocation paths, not only secret storage. The practitioner conclusion is that agent access reviews need to cover tool reach, execution scope, and delegated authority together.
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.
- 28% of secrets incidents now originate outside code repositories, in Slack, Jira, and Confluence, and are 13% more likely to be critical than code-based leaks.
A question worth separating out:
Q: Should organisations treat AI agents like human users in IAM?
A: No. Human IAM assumes a person logs in, works within a session, and can be reviewed later as a stable identity holder. Agents can act at machine speed, across multiple systems, and with changing runtime context, so they need identity governance built around execution and delegation rather than human authentication patterns.
👉 Read our full editorial: AI agents and secrets handling are becoming the new control plane
