Use case sources
Source reports and analysis supporting this case are listed below. AITBM interpretation and any indicative scoring are derived from this public evidence.
Adversa demonstrated a Grok web-chat browsing path in which a hostile page induced runtime decryption of attacker instructions and privileged navigation to an attacker URL containing private session context and conversation prompts.
ASSESSED SYSTEM
The Adversa-reproduced xAI Grok web-chat browsing configuration as of August 19, 2026, receiving a hostile page during summarization.
OUT OF SCOPE
Gemini and GitHub Copilot CLI follow-up findings, unrelated Grok configurations, real victim data theft, and internal provenance-label behavior are outside scope.
Architecture: Tool-Calling LLM / Connected GenAI (decision tree Q3) — A user-driven web-chat assistant invoked code and privileged navigation tools; longer-horizon autonomous task control is not established. Tier 2: Tier 2 representative public-facing service scenario; the original source does not establish every operator tier.
Documented attack or failure path
- A user asked Grok to summarize an attacker-controlled page.
- Its code runtime decrypted instructions embedded in that page.
- Grok used its browsing/navigation capability to request an attacker URL with session and prompt data.
Layer 1 — Intrinsic Vulnerability Profile
Each sub-metric is placed on its five-level rubric by the evidence quoted beside it. Missing applicable evidence remains unknown. The displayed midpoint and interval are scenario values, not inferred control performance.
| Sub-metric | Score | Rubric basis | Evidence |
|---|---|---|---|
| Robustness (Ro) — scenario interval 0.00–1.00 (midpoint 0.50), Tier 2 MVT 0.50 indeterminate | |||
| Fairness (Fa) — scenario interval 0.00–1.00 (midpoint 0.50), Tier 2 MVT 0.55 indeterminate | |||
| Transparency (Tr) — scenario interval 0.00–1.00 (midpoint 0.50), Tier 2 MVT 0.50 indeterminate | |||
| Privacy (Pr) — scenario interval 0.00–1.00 (midpoint 0.50), Tier 2 MVT 0.55 indeterminate | |||
| Containment (Cn) — scenario interval 0.00–0.88 (midpoint 0.44), Tier 2 MVT 0.55 indeterminate | |||
| Cn-1Scope Enforcement | 0.00w 0.12 | The browsing tool allowed a model-directed request to an attacker endpoint carrying private session data outside authorized scope, matching Cn-1 0.00. | Adversa observed Grok navigation emit private session context and conversation prompts to an attacker URL, with no effective egress or consent gate on that path.source: primary report |
Unknown, not N/A: 25 applicable sub-metrics lack admissible public evidence. The lower, midpoint, and upper scenarios evaluate each at 0.00, 0.50, and 1.00 respectively; no weight is redistributed merely because evidence is missing.
Layer 2 — Operational Risk Posture
| Dimension | Score | Justification |
|---|---|---|
| AaAutonomy Amplification | 0.50w 0.25 | Representative activity level for the documented bounded AI path; deployment-specific autonomy was not measured. |
| AsAttack Surface Exposure | 0.75w 0.35 | Representative exposure of the documented entry path; this is a scenario assumption and not a census of all operators. |
| CpCascade Potential | 1.00w 0.20 | No verified System Dependency Graph or DGC is published, so framework worst-case Cp default applies.GDCP: worst-case default — no verified dependency graph published elevated |
| RfRemediation Feasibility | 0.50w 0.20 | A specific patch or configuration change is documented; repair feasibility is an inferred representative scenario, not measured recovery time. |
Nelevated = 1 (dimensions strictly above 0.75) → CRM = 1.00.
Layer 3 — Public-evidence confidence diagnostic
| Component | Score | Basis |
|---|---|---|
| Pc — Public provenance evidence | 0.25 | Minimal public provenance identifies the affected path but supplies no operator assessment pack, signed configuration inventory, or repeated metric battery. |
| Ec — Public evaluation coverage | 0.03 | coverage 0.04 (1 of 26 applicable sub-metrics) × independence 0.80 × fidelity 0.95. No Full, Standard, or Lite pathway is claimed for a retrospective article. |
| Tf — Public-evidence freshness | 0.60 | Evidence dated 2026-08-20; age 59 days on the workpaper reference date. Components: C_monitor 0.60 · T_calendar 0.63. Binding term: C_monitor. Evidence reference is 2026-10-18, 59 days after earliest substantive public evidence (2026-08-20). C_monitor uses the conservative Tier 2 public-evidence default because usable monitoring-coverage evidence is unavailable; it does not assert no deployment telemetry. No C_event cap is asserted from research or an advisory without a dated victim incident. No generic C_evidence cap is assigned from missing public inputs. Indicative ERS uses normalized ACI = 1.00 for comparison only. |
Public-evidence ACI = (Pc × Ec × Tf)1/3 = 0.16 — diagnostic status: Invalid as assessment-of-record evidence. It describes the evidence available to this case study, not the assurance of the underlying system, and is not inserted into the normalized-assurance scenario ERS.
Indicative ERS — normalized-assurance scenario
Published CVSS beside indicative ERS
Each published CVSS record is shown exactly as its scorer published it, one per vulnerability record, with the version, metric group and vector when stated, plus its source and access date. Records are never combined or inferred from a CVE's existence.
INDICATIVE ERS · NORMALIZED-ASSURANCE SCENARIO
4.0 midpoint, interval 1.1–6.9; Low-Moderate scenario band; ACI fixed at 1.00. The published CVSS records do not enter this calculation.
PUBLISHED CVSS
CVSS — no applicable published score verified.
No published CVSS score matching this exact assessed path was verified.
CVSS describes an individual vulnerability as its scorer published it. Indicative ERS describes the assessed AI deployment under the normalized-assurance scenario, so the two values are not direct equivalents and neither replaces the other.
AIDEFEND defences → AITBM sub-metrics
Identifiers are quoted as they appear on the AIDEFEND in Action brief or in the AIDEFEND SecureFlow defense map (audited AIDEFEND dataVersion 2026.10.15); the sub-metric mapping is AITBM's own, from the specification's AIDEFEND tables reconciled at catalogue data version 2026.10.15. AIDEFEND renumbers identifiers between releases, so the data version travels with every mapping and neither side's IDs should be cited without one. A mapping identifies a possible evidence route; a recommendation does not prove that the control was implemented or effective and receives no scoring credit by itself.
| Technique | Defence | Priority | Evidences |
|---|---|---|---|
| AID-H-017.007 | Dual-LLM Isolation PatternExact upstream page defense ID, verified against AIDEFEND dataVersion 2026.10.15. Presence supplies no score credit. | Candidate evidence route | Cn-5 Cn-7 |
| AID-H-018.005 | Value-Level Capability Metadata & Data Flow Sink EnforcementExact upstream page defense ID, verified against AIDEFEND dataVersion 2026.10.15. Presence supplies no score credit. | Candidate evidence route | Cn-1 Cn-6 Cn-7 |
| AID-I-001.004 | Sandbox Network Egress RestrictionsExact upstream page defense ID, verified against AIDEFEND dataVersion 2026.10.15. Presence supplies no score credit. | Candidate evidence route | Pr-2 Cn-7 |
WHAT THIS CASE TEACHES
Adversa demonstrated a Grok web-chat browsing path in which a hostile page induced runtime decryption of attacker instructions and privileged navigation to an attacker URL containing private session context and conversation prompts.
Sources: Official AIDEFEND in Action brief · AIDEFEND SecureFlow — Cryptographic Context Injection in AI Web Research · Adversa original Grok proof of concept, 2026-08-20