SAF-T[XXXX]: [Technique Name]

September 2, 2026 ยท View on GitHub

Overview

  • Tactic: [Primary Tactic (ATK-TAXXXX); Secondary Tactic (ATK-TAXXXX), if applicable]
  • Framework Profiles: [SAF Core / MCP / Code-Agent / RAG and Memory / Financial-Agent / Model-Lifecycle]
  • Lifecycle Status: [Active / Deprecated]
  • Technique ID: SAF-T[XXXX]
  • Research Packet: research/techniques/SAF-TXXXX
  • Traceability Ledger: traceability-ledger.yml
  • Documentation Status: [Draft / Under Review / Stable / Deprecated]
  • Evidence Status: [Observed / Demonstrated / Research-Derived / Hypothesized]
  • Severity: [Critical / High / Medium / Low]
  • Severity Rationale: [One sentence explaining the rating and the conditions under which it applies]
  • First Observed: [YYYY-MM-DD and source / Not observed in production]
  • Last Updated: [YYYY-MM-DD]

Scope

[State precisely what adversary behavior this technique covers and the security boundary it crosses.]

In Scope

  • [Behavior, mechanism, or outcome included in this technique]
  • [Relevant MCP component, capability, or trust boundary]

Out of Scope

  • [Closely related behavior covered by another SAF technique]
  • [Behavior that may look similar but has a different mechanism or outcome]

Distinguishing Characteristics

[Explain how an analyst can distinguish this technique from its nearest neighbors. Name and link those techniques where appropriate.]

Description

[Define the technique in two to four concise paragraphs. Explain the adversary objective, the MCP-specific mechanism, the affected trust boundary, and why normal platform controls may not prevent it.]

[Separate demonstrated behavior from inference. Do not place mitigation guidance or unsupported impact claims in this section.]

Attack Vectors

  • Primary Vector: [Principal delivery or exploitation path]
  • Secondary Vectors:
    • [Secondary vector and when it applies]
    • [Secondary vector and when it applies]
  • Affected Components: [MCP host, client, server, transport, tool, resource, prompt, model, memory, registry, or external service]
  • Trust Boundary Crossed: [Boundary the adversary crosses or abuses]

Technical Details

Prerequisites

  • [Required access, capability, configuration, or victim action]
  • [Required weakness or missing control]
  • [Environmental condition, if applicable]

Attack Flow

  1. Reconnaissance or Setup: [How the adversary identifies or prepares the opportunity]
  2. Delivery: [How attacker-controlled input, software, identity, or state reaches the target]
  3. Trigger or Execution: [The MCP or agent action that activates the technique]
  4. Boundary Crossing: [The security decision, trust assumption, or control that fails]
  5. Objective: [The immediate adversary outcome]
  6. Follow-On Activity: [Likely persistence, escalation, collection, exfiltration, or impact]

Example Scenario

[Describe one realistic end-to-end scenario. Identify the actor, entry point, vulnerable assumption, observable behavior, and outcome.]

{
  "example": "Use a sanitized MCP message, tool definition, event, or configuration",
  "placeholder": "Do not include live credentials, destructive commands, or operational secrets"
}

Variants and Sub-Techniques (Optional)

ID or NameMechanismDistinguishing Observables
SAF-T[XXXX].001 or [Variant Name][How this variant works][Signals unique to the variant]

Architecture or Attack-Flow Diagram (Optional)

flowchart LR
  A[Adversary-controlled input] --> B[MCP or agent component]
  B --> C[Failed trust boundary]
  C --> D[Adversary objective]

Evidence and Current State

Evidence Summary

Claim IDClaimEvidence StatusSource ID and SourceLimitations
SAF-T[XXXX]-C001[Core technique claim][Observed / Demonstrated / Research-Derived / Hypothesized]SRC-[source]: Primary source[What the source does not establish]

Current State

  • Affected Environments: [Known products, deployment patterns, or preconditions]
  • Known Exploitation: [Observed activity, public demonstrations, or none identified]
  • Available Protections: [Relevant platform controls, patches, or protocol guidance]
  • Residual Risk: [What remains possible after common protections are applied]

Known Breaches and Vulnerabilities

Event or IdentifierDate and EnvironmentImpact and RemediationRelationship to This TechniqueEvidence Limitation
[Incident, CVE, GHSA, or demonstration][Event/publication date; affected product, versions, and configuration][Observed or bounded potential consequence; patch or mitigation status][Direct production incident / direct vulnerability / direct demonstration / enabling vulnerability / adjacent][What the evidence does not establish]

Real-World Incidents or Demonstrations (Optional)

[Incident or Demonstration Name] ([Date])

[Describe only what the cited source establishes. Explain the connection to this technique and any important differences from the documented MCP scenario.]

Impact Assessment

DimensionRatingRationale and Conditions
Confidentiality[Critical / High / Medium / Low / None][Data exposed and required conditions]
Integrity[Critical / High / Medium / Low / None][State or decisions altered and required conditions]
Availability[Critical / High / Medium / Low / None][Disruption and required conditions]
Scope[Local / Adjacent / Multi-System / Ecosystem-Wide][Expected blast radius and limiting factors]

Severity Conditions

  • Severity increases when: [Privileges, connectivity, automation, sensitive data, or missing controls]
  • Severity decreases when: [Isolation, scoped credentials, approval gates, or other constraints]

Detection Methods

Required Telemetry

SourceEvents or ActionsRequired FieldsCollection Notes
[MCP host/client/server audit log][Relevant request, response, or lifecycle event][Timestamp, session, actor, server, tool, arguments, result, approval state][Correlation or retention requirement]
[Identity, endpoint, network, model, or application log][Relevant activity][Fields needed by the analytic][Clock, normalization, or privacy considerations]

Indicators of Compromise (IoCs)

  • [Artifact, identifier, file, endpoint, account, or configuration change]
  • [Artifact, identifier, file, endpoint, account, or configuration change]
  • [None known, if the technique produces no reliable durable artifact]

Behavioral Indicators

  • [Observable sequence or deviation that may indicate the technique]
  • [Cross-source correlation that increases confidence]
  • [Condition that separates suspicious behavior from normal administration]

Detection Analytic

The standalone example analytic is maintained in detection-rule.yml. Do not duplicate the complete rule in this document.

  • Analytic Goal: [What behavior the rule detects]
  • Rule Status: [Experimental / Test / Stable]
  • Detection Logic: [Selections, correlation, sequence, or threshold in plain language]
  • Correlation Window: [Duration or sequence boundary, if applicable]
  • Known False Positives: [Expected legitimate activity]
  • Known Limitations: [Blind spots, evasion opportunities, or unavailable telemetry]
  • Tuning Guidance: [Environment-specific thresholds, allowlists, or baselines]

Validation

  • Test Data: test-logs.json
  • Validation Script: test_detection_rule.py
  • Expected Result: [Number of positive and negative cases and required outcome]
  • Detection Maturity: [Proposed / Syntax Validated / Fixture Tested / Telemetry Replay Tested / Field Evaluated]
  • Last Validated: [YYYY-MM-DD]
  • Feasibility Waiver: [None / Specific reason representative validation is not currently possible]

Mitigation Strategies

Preventive Controls

  1. SAF-M-X: Control Name: [How the control prevents or constrains this technique]
  2. SAF-M-X: Control Name: [Implementation requirement or boundary]
  3. [Platform or Protocol Control]: [Control not represented by an existing SAF mitigation, with citation]

Detective Controls

  1. SAF-M-X: Control Name: [Telemetry, alerting, or review requirement]
  2. SAF-M-X: Control Name: [How the control increases detection confidence]

Response Procedures

Immediate Actions

  • [Contain the session, identity, server, tool, or affected resource]
  • [Revoke or rotate exposed credentials where applicable]

Investigation Steps

  • [Preserve and correlate the required telemetry]
  • [Determine entry point, affected scope, and follow-on activity]

Remediation

  • [Remove the root cause or unsafe configuration]
  • [Restore affected state and validate recovery]
  • [Add regression coverage or monitoring for recurrence]
TechniqueRelationshipDistinction
SAF-TXXXX: Technique Name[Prerequisite / Alternative / Co-occurring / Follow-On / Overlapping][Why the techniques are related but not duplicates]
SAF-TXXXX: Technique Name[Relationship][Boundary between the techniques]

MITRE ATT&CK Mapping

ATT&CK IDTechniqueMapping TypeRationale
TXXXX[ATT&CK Technique Name][Direct / Analogous][Behavioral correspondence and important limitations]

Additional Framework Mappings (Optional)

FrameworkIDNameRationale
[MITRE ATLAS / OWASP / NIST / Other][Identifier][Control or technique name][Why the mapping applies]

References

  1. SRC-[source]: Model Context Protocol Specification - [Relevant section and claim supported]
  2. SRC-[source]: Primary source title - Author or Organization, Year - [Claim supported]
  3. SRC-[source]: Additional source title - Author or Organization, Year - [Claim supported]

Version History

VersionDateChangesAuthor
0.1[YYYY-MM-DD]Initial draft[Name or handle]