AG-T-01Level 1 · Signal
Agent credentials or tokens exposed
- Threat
- Neutral
- Level 1 · Signal
A Threat signal for an AI agent from exposure monitoring (EXPO, exposed secret for a service identity): the agent's key, token or password was found in a public repository, a paste site or a breach dump.
Classification
- Risk domain One of 9 areas of human risk, from social engineering to readiness and response. Every signal belongs to one.
- Evidence level
- Maturity practices One capability a program performs, scored on its own: See, Understand, Act, Prove, Govern and Culture.
- Leads to The kind of breach the evidence beneath it points toward, each anchored to a Verizon DBIR or VERIS pattern or an FBI IC3 category.
- NIST CSF 2.0
-
- ID.RA-03
- MITRE ATT&CK
-
- T1528
The definition, in detail
Definition
Whoever has it can act as the agent.
Example
A deployment agent's API key is committed to a public code repository by a developer; the monitoring feed matches it within hours and the key is revoked.
How it is measured
How it is used
Programs count "Agent credentials or tokens exposed" per ai agent from Breach & dark-web exposure and read it beside the other AI agents signals; it feeds 0 cohorts, 0 sequences and 2 breach scenarios.
A "agent credentials or tokens exposed" record is evidence of what reaches the person (the threat side of the model). It says nothing on its own about what the person did.
Technical mappings
Framework mappings; validate for your use case.
Continue exploring
"Agent credentials or tokens exposed" (AG-T-01), Human Risk Management Framework v2.0.0, Living Security, CC BY 4.0. https://www.humanriskmanagement.com/taxonomy/signals/ag-t-01-agent-credentials-or-tokens-exposed
Part of the open HRM Taxonomy, CC BY 4.0. Download the taxonomy as JSON · Version history. This page describes one signal.
The initial assessment
Find your level.Then fix what matters.
18 questions, about 4 minutes and nothing to type before the result: your level, a score for each practice and three first playbooks, each Easy, Medium or Hard.