AG-B-01Level 1 · Signal
Grants agents broad or standing permissions
A risky Behavior signal from identity governance (IGA, agent scope grant): this person approved an AI agent or service identity with wide scopes or permissions that never expire.
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
-
- PR.AA-05
- MITRE ATT&CK
-
- T1528
The definition, in detail
Definition
The agent now holds more standing access than its task needs.
Example
An automation engineer grants a reporting agent organization-wide read and write access with no expiry because the narrower scope needed an extra ticket.
How it is measured
- Source
- IGA, PAM & entitlements
- Subject
- AI agent
- Event
- Agent scope grant
- Risk domain
- AI agents
- Provenance
- Framework research
How it is used
Programs count "Grants agents broad or standing permissions" per ai agent from IGA, PAM & entitlements and read it beside the other AI agents signals; it feeds 0 cohorts, 0 sequences and 2 breach scenarios.
A "grants agents broad or standing permissions" event is evidence of behavior under pressure. It is one observed action, and on its own it is no proof of compromise.
Technical mappings
Framework mappings; validate for your use case.
Library indicators
The detailed observations in the indicator library with the same risk domain, dimension and polarity as this signal.
- I.0465Attempts to override AI guardrails
- I.0466Launches AI agents without approval
- I.0467Runs privileged AI workflows without logging
- I.0470Configures AI agents to bypass safeguards
- I.0471Manipulates AI models to bias outputs
- I.0473Schedules autonomous AI tasks without review
- I.0474Disables AI workflow logging
- I.0475Uses AI agents outside role authority
Continue exploring
"Grants agents broad or standing permissions" (AG-B-01), Human Risk Management Framework v2.0.0, Living Security, CC BY 4.0. https://www.humanriskmanagement.com/taxonomy/signals/ag-b-01-grants-agents-broad-or-standing-permissions
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.