Insider Threat Matrix™Insider Threat Matrix™
HumanSynthetic
Detections
Preventions
Github

Synthetic Subject Logging Gaps

Synthetic subject logging gaps occur when the logs, traces, or audit records needed to reconstruct synthetic subject behavior are missing, incomplete, fragmented, inconsistent, or untrustworthy. This may involve absent prompt logs, missing tool-call arguments, incomplete runtime traces, weak non-human identity attribution, inaccessible vendor telemetry, or downstream effects that cannot be tied to a recorded synthetic subject action.

 

This condition frustrates investigation because synthetic subject activity often spans multiple evidence sources. A single action may involve a prompt, retrieved context, model output, tool call, service identity, connector, runtime process, and downstream system event. If those records are not captured and correlated, investigators may be unable to determine what happened, why it happened, which synthetic subject acted, or how to contain recurrence.

 

The primary risk is evidentiary incompleteness. Downstream systems may show that a record changed, data moved, a message was sent, or a process ran, while the synthetic subject action that caused it is not visible. This can force investigators to rely on model narration, partial application logs, or inference rather than an authoritative action trail.

 

A related risk is evidentiary unreliability. Where the synthetic subject can access or alter its own logs, traces, audit directories, monitoring configuration, or runtime records, the available evidence may no longer be trustworthy. This creates uncertainty about both the observed action and the absence of other actions.

 

Investigators should review prompt logs, response logs, tool-call logs, runtime traces, non-human identity activity, downstream audit logs, logging sidecars, Security Information and Event Management (SIEM) ingestion, sequence numbers, timestamps, clock synchronization, vendor telemetry, and logging configuration changes. Particular attention should be given to missing arguments, orphaned downstream effects, sequence gaps, clock skew, sudden logging disablement, agent access to audit paths, and agents or tools operating without attached logging controls.

 

Investigative Relevance

Synthetic subject logging gaps are relevant because they frustrate observation, explanation, attribution, or containment. Without complete and trustworthy logs, investigators cannot reliably reconstruct the synthetic subject’s prompt, context, tools, actions, outputs, or side effects.

 

This section is especially relevant where synthetic subjects call tools directly, use service accounts, invoke Model Context Protocol (MCP) servers, run in local or vendor-managed runtimes, execute commands, write to filesystems, interact with multiple systems, or bypass a centralized broker that would otherwise capture side-effecting actions.

Subsections (5)

ID Name Description
OP005.004Ambiguous Actor Attribution

Ambiguous actor attribution occurs when available logs or records show that an action happened, but do not identify the specific synthetic subject, human operator, tool, connector, workflow, or vendor-controlled component that caused it. The evidence may be intact and accurate, but still too general to support attribution.

 

This condition is distinct from log deletion or trace tampering. In ambiguous actor attribution, the problem is not necessarily that evidence was removed or altered. The problem is that the recorded actor is too broad, shared, or indirect to identify the real source of the action.

 

The primary risk is collapsed actor identity. A record update, message, tool call, or system change may be logged under a shared service account, delegated human identity, generic application identity, or workflow bot. The log may truthfully record that the shared identity acted, but fail to show which synthetic subject, operator prompt, tool call, or invocation path produced the action.

 

A related risk is containment uncertainty. If investigators cannot identify the responsible actor, they may have to disable broad identities, revoke multiple connectors, suspend unrelated workflows, or take larger containment actions than necessary. Conversely, they may fail to contain the true source if the apparent identity is only a shared proxy.

 

Investigators should review identity provider logs, service account ownership, non-human identity records, OAuth grants, connector identities, prompt and response logs, tool-call records, session context, agent identifiers, vendor audit fields, and actor attribution metadata. Particular attention should be given to shared service accounts, missing agent IDs, actions recorded only under a human identity, multiple agents using one credential, and vendor logs that collapse model, tool, and user activity into one actor.

 

Investigative Relevance

Ambiguous actor attribution is relevant because synthetic subjects often act through borrowed, shared, delegated, or vendor-managed identities. Even complete logs may be insufficient if they identify only the account used, not the synthetic subject or invocation that caused the action.

 

This condition is especially relevant where synthetic subjects use shared service accounts, delegated user sessions, marketplace connectors, Model Context Protocol (MCP) servers, human-attributed actions, vendor-hosted AI features, or orchestration platforms with multiple agents operating through the same identity.

OP005.001Missing or Incomplete Action Logs

Missing or incomplete action logs occur when the records needed to reconstruct synthetic subject activity are absent, partial, fragmented, or not retained long enough for investigation. This may include missing prompts, responses, retrieved context, tool-call arguments, tool results, non-human identity records, runtime traces, or downstream action identifiers.

 

This condition frustrates investigation because a synthetic subject action often spans multiple systems. Investigators may see a record change, outbound request, message, command, or file write without the corresponding prompt, context, tool call, or model output that caused it.

 

The primary risk is evidentiary incompleteness. Without complete action logs, investigators may be unable to determine what the synthetic subject was asked, what information it used, which tool it selected, what arguments it passed, what result it received, or why a downstream side effect occurred.

A related risk is retention failure. Short-lived runtime traces, vendor-managed logs, local developer sessions, temporary files, or uncollected tool outputs may disappear before an incident is recognized. This can leave only partial application logs or the synthetic subject’s own explanation, neither of which should be treated as sufficient evidence.

 

Investigators should review prompt logs, response logs, retrieval logs, tool-call records, runtime traces, non-human identity events, downstream audit logs, retention settings, vendor telemetry availability, and log ingestion status. Particular attention should be given to missing tool arguments, absent results, incomplete retrieval provenance, missing requester identity, short retention periods, and evidence sources that were not collected into the central logging system.

 

Investigative Relevance

Missing or incomplete action logs are relevant because investigators cannot reliably explain, attribute, scope, or contain synthetic subject behavior without a complete action trail. The absence of logs may be as significant as the content of the logs that remain.

 

This sub-section is especially relevant where synthetic subjects call tools directly, use local runtimes, operate through vendor platforms, invoke Model Context Protocol (MCP) servers, generate files, execute commands, or act across systems whose logs are not centrally correlated.

OP005.002Self-Directed Log or Trace Tampering

Self-directed log or trace tampering occurs when a synthetic subject can read, modify, delete, redact, suppress, or reconfigure the logs, traces, audit records, or monitoring systems that record its own behavior. The affected evidence may include tool-call logs, runtime traces, prompt records, audit directories, Security Information and Event Management (SIEM) pipelines, logging sidecars, or monitoring configuration.

 

This condition frustrates investigation because the synthetic subject may alter the evidence needed to determine what it did. Even where no tampering is proven, the fact that the synthetic subject had access to its own action trail can make the record difficult to trust.

 

The primary risk is evidence unreliability. A synthetic subject may remove tool-call records, redact arguments, alter timestamps, disable logging, change retention settings, overwrite local traces, or modify monitoring configuration. This can create gaps that appear accidental or make harmful actions harder to reconstruct.

 

A related risk is containment delay. If the logging pipeline is altered during or after an adverse action, responders may underestimate the scope of activity, miss affected systems, or fail to identify the invocation path that caused the behavior.

 

Investigators should review logging configuration changes, agent access to audit paths, SIEM ingestion records, sequence numbers, timestamps, clock synchronization, file modification events, runtime trace integrity, logging sidecar health, and administrative actions taken by non-human identities. Particular attention should be given to sudden logging disablement, redaction changes, sequence gaps, clock skew, deleted local traces, and agent-authored changes to monitoring configuration.

 

Investigative Relevance

Self-directed log or trace tampering is relevant because the synthetic subject’s own evidentiary trail must be protected from the subject being investigated. Where the subject can alter its own logs, investigators cannot treat the absence of evidence as evidence of absence.

 

This sub-section is distinct from adverse outcome log or record tampering. Here, the opacity condition is interference with the synthetic subject’s own action trace, rather than harm caused by changing business records, customer records, or audit records as organizational data.

OP005.005Shared Non-Human Identity Attribution Gap

Shared Non-Human Identity (NHI) attribution gap occurs when multiple synthetic subjects, users, sessions, tools, or workflows act through the same service account, credential, token, connector identity, or application identity. The logs may show that the shared identity acted, but not which synthetic subject, operator prompt, session, or human principal caused the action.

 

This condition frustrates investigation because the evidence is too broad to support reliable attribution. The issue is not necessarily missing logs or deleted records. The issue is that the recorded actor is a shared identity that collapses multiple possible actors into one audit trail.

 

The primary risk is loss of accountability. A database update, message, tool call, file access, Application Programming Interface (API) request, or workflow action may be logged under a single shared NHI. Investigators may be unable to determine whether the action was caused by one agent instance, another agent instance, an automated workflow, a connected tool, or a human operator acting through the same credential.

 

A related risk is containment uncertainty. If the responsible synthetic subject cannot be identified, responders may need to disable the entire shared identity, interrupt multiple workflows, revoke broad connectors, or suspend legitimate operations. Conversely, containment may fail if the true actor continues to operate through the same shared identity after one suspected agent is disabled.

 

Investigators should review service account ownership, credential assignment, token issuance, connector identity records, non-human identity activity, prompt and response logs, session identifiers, agent identifiers, human-principal binding, OAuth grants, Privileged Access Management (PAM) records, and downstream audit logs. Particular attention should be given to one credential exhibiting multiple behavioral patterns, concurrent use of the same identity, actions with no resolvable originating principal, static long-lived credentials, and service accounts used by multiple synthetic subjects.

 

Investigative Relevance

Shared NHI attribution gap is relevant because synthetic subjects often act through machine identities rather than direct human accounts. When multiple agents or workflows share one NHI, even complete logs may be insufficient to identify the true source of an action.

 

This condition is especially relevant where synthetic subjects use shared service accounts, static API keys, marketplace connectors, Model Context Protocol (MCP) servers, automation tokens, application identities, or vendor-managed credentials that do not preserve the originating user, session, agent, and invocation context.

OP005.003Tool-Call to Side-Effect Mismatch

Tool-call to side-effect mismatch occurs when downstream system effects cannot be reconciled with recorded synthetic subject tool calls. A database update, message send, file write, process launch, configuration change, or external request may exist without a matching tool-call record, or the recorded tool call may not explain the observed effect.

 

This condition frustrates investigation because synthetic subject action often becomes visible only through downstream side effects. If tool-call logs and system-of-record telemetry do not align, investigators cannot reliably determine whether the effect was caused by the synthetic subject, a connected tool, a human user, a service account, or another workflow.

 

The primary risk is orphaned action evidence. Downstream systems may show that something changed, but the corresponding synthetic subject decision, tool call, parameter set, or result is missing or inconsistent. This can prevent investigators from identifying the originating prompt, affected tool, responsible identity, or scope of similar actions.

 

A related risk is hidden tool behavior. A connected tool may perform additional actions beyond the model-visible request, such as forwarding data, modifying records, spawning processes, or calling external services. The synthetic subject’s recorded tool call may appear benign while the tool’s side effects show a broader action.

 

Investigators should review tool-call logs, tool arguments, tool results, downstream application logs, database audit records, message headers, file-system events, process telemetry, web proxy logs, connector records, and non-human identity activity. Particular attention should be given to orphaned downstream effects, benign-looking tool calls followed by high-impact changes, mismatched parameters, missing results, and tool behavior that exceeds the recorded request.

 

Investigative Relevance

Tool-call to side-effect mismatch is relevant because the investigator must connect synthetic subject decisions to real system effects. A complete investigation requires both the model-visible tool call and the authoritative downstream evidence of what actually happened.

 

This sub-section is especially relevant where synthetic subjects call tools that write to systems, send communications, execute commands, invoke APIs, operate through MCP servers, or interact with external services that may perform actions not fully reflected in the synthetic subject’s own logs.