Who Did the Agent Act For?

Part I

Problem Definition

An action can identify the immediate workload yet fail to preserve the human or service principal, delegation purpose, and actor chain on whose behalf the agent acted [R1] [R2].

This note treats who did the agent act for? as a bounded control question. It does not infer universal product behavior from a paper, standard, interface screenshot, or single test. A demonstrated result applies only to the cited configuration; an authoritative source defines a requirement or design direction but does not certify an implementation. ACE therefore asks whether the tested system can produce the required behavior and evidence under declared versions, policies, topology, identities, and failure conditions.

The operational distinction is between a claim and a control that can be re-performed. The positive control is: A finance agent submits an approved read request on behalf of a named employee under a specific task. The adversarial condition is: The same action arrives with only a service identity, a stale user field, or a broken delegation chain. A useful result must show both that authorized work remains possible and that the prohibited path is stopped before an irreversible side effect. Missing fields are classified as insufficient evidence, not silently converted into a pass.

Real-world impact

• Investigators may know which service called an API but not who authorized the business action.
• Shared execution paths can make two users' actions indistinguishable during dispute or incident response.
• A control claim without versioned evidence can mislead procurement, audit, incident response, and system owners.
• Failing closed without a positive control can conceal a denial-of-service design rather than demonstrate trustworthy behavior.

Part II

Mitigation Direction

Research-backed direction

1. 01
   research proposed

   Assign workload identities in a trust domain instead of identifying agents only by network location or shared secrets [R3].

2. 02
   research proposed

   Preserve subject and actor as separate claims when exchanging authority across services [R2].

3. 03
   research proposed

   Record the associated identities and entities with every consequential audit event [R4].

LogionOS engineering mapping

Implementation hypotheses only. No production validation is claimed.

1. 01
   implementation hypothesis

   Add a versioned policy object for who did the agent act for? and keep its decision inputs outside model-writable context.

2. 02
   implementation hypothesis

   Generate a signed technical receipt linking actor, request, policy version, decision, enforcement point, and observed outcome.

3. 03
   implementation hypothesis

   Export missing evidence explicitly as insufficient evidence and limit every claim to the tested configuration.

Part III

Consequences and Research Agenda

Consequences

• Investigators may know which service called an API but not who authorized the business action.
• Shared execution paths can make two users' actions indistinguishable during dispute or incident response.
• A failed acceptance test requires the related capability claim to remain not demonstrated or insufficient evidence.
• A passing test supports only the declared configuration and does not establish universal safety.

Second-order effects

• Stronger enforcement can increase latency, state, operational dependencies, and legitimate denials.
• More evidence can increase privacy and retention exposure unless raw content is minimized and access-controlled.
• A detector or policy service can become a new failure point and must have explicit fail behavior.
• Attackers may adapt to published checks, so the public test direction should be paired with private regression variants.

Limitations

• Several cited AI-agent and reasoning-security sources are preprints or bounded experiments; they are identified as such in the references.
• The proposed ACE acceptance test has not yet been run across all incumbent and AI-native implementations.
• Cryptographic integrity proves that an artifact was not altered after commitment; it does not prove that the artifact was true, complete, or correctly interpreted.
• Legal and contractual applicability remains deployment- and jurisdiction-specific.

Open research questions

1. How should an agent represent multiple principals with different authority?
2. Which identity claims survive cross-organization federation without semantic ambiguity?
3. Which evidence fields are mandatory for a demonstrated result, and which may be not applicable?
4. How should continuous regression detect policy, model, tool, and provider drift after the initial test?

Sources

References

1. [R1]
   NIST NCCoE Software and AI Agent Identity and Authorization Concept Paper

   draft-concept-paper · authoritative-standard

2. [R2]
   RFC 8693: OAuth 2.0 Token Exchange

   published · authoritative-standard

3. [R3]
   SPIFFE ID Specification

   published · authoritative-standard

4. [R4]
   NIST SP 800-53 Rev. 5

   published · authoritative-standard

Record

Publication Record

Recommended citation

Ma, Chris. “Who Did the Agent Act For?.” ACE Research Note ACE-RN-2026-004, v1.0, 2026.

Corrections

No corrections recorded.

Organizational disclosure

ACE Research and LogionOS share organizational affiliation. LogionOS mappings in this note are implementation hypotheses, not independently validated product claims.

Evidence boundary

This note synthesizes cited public research and defines an ACE acceptance direction. It does not report a completed cross-vendor experiment unless explicitly stated, and it contains no private ACE prompts, holdout identifiers, customer data, or raw model responses.