Exam Bundle

A forged policy document is rejected or quarantined and the agent cites only authorized versioned sources. This is evidence for a different corrective change: Validate trusted document provenance, restrict source updates, and record retrieval lineage before ingesting new context. That other change addresses: A question-answering agent indexes mutable policy documents without content verification, allowing poisoned text to contaminate answers. It does not validate the specific Silverline Insurance remediation for: A generative assistant returns disallowed harmful instructions because a high overall helpfulness score is the only release metric. The necessary check instead is: A reviewed unsafe-prompt suite elicits the required refusals while permitted requests remain useful.

A retention test confirms expired personal prompts are deleted while required non-sensitive audit markers remain. This is evidence for a different corrective change: Set data-minimizing storage and deletion policies across prompt, retrieval, logging, and model telemetry systems. That other change addresses: A legal-assistance assistant stores personal prompts indefinitely although contractual retention limits require rapid deletion. It does not validate the specific Silverline Insurance remediation for: A generative assistant returns disallowed harmful instructions because a high overall helpfulness score is the only release metric. The necessary check instead is: A reviewed unsafe-prompt suite elicits the required refusals while permitted requests remain useful.

An authorized reviewer reproduces a local feature contribution for a frozen case without treating it as causal proof. This is evidence for a different corrective change: Enable an appropriate model-explainability method, document its limitations, and link explanations to model versions. That other change addresses: A decision model provides probability scores but the governance report offers no reproducible local explanation for an adverse case. It does not validate the specific Silverline Insurance remediation for: A generative assistant returns disallowed harmful instructions because a high overall helpfulness score is the only release metric. The necessary check instead is: A reviewed unsafe-prompt suite elicits the required refusals while permitted requests remain useful.

Use Secret Manager or a secured secret-injection workflow and revoke exposed credentials. This action could be suitable for a different engineering incident: A pipeline embeds production database passwords in plain text inside model-training container environment files committed to source control. It does not directly correct the reported Northgate Clinical Systems failure: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The discriminating acceptance check here is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

Validate trusted document provenance, restrict source updates, and record retrieval lineage before ingesting new context. This action could be suitable for a different engineering incident: A question-answering agent indexes mutable policy documents without content verification, allowing poisoned text to contaminate answers. It does not directly correct the reported Northgate Clinical Systems failure: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The discriminating acceptance check here is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

Enable an appropriate model-explainability method, document its limitations, and link explanations to model versions. This action could be suitable for a different engineering incident: A decision model provides probability scores but the governance report offers no reproducible local explanation for an adverse case. It does not directly correct the reported Northgate Clinical Systems failure: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The discriminating acceptance check here is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

An authorized reviewer reproduces a local feature contribution for a frozen case without treating it as causal proof. This is evidence for a different corrective change: Enable an appropriate model-explainability method, document its limitations, and link explanations to model versions. That other change addresses: A decision model provides probability scores but the governance report offers no reproducible local explanation for an adverse case. It does not validate the specific Northgate Clinical Systems remediation for: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The necessary check instead is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

A repository scan finds no active plaintext secret and the authorized training task obtains it only at execution time. This is evidence for a different corrective change: Use Secret Manager or a secured secret-injection workflow and revoke exposed credentials. That other change addresses: A pipeline embeds production database passwords in plain text inside model-training container environment files committed to source control. It does not validate the specific Northgate Clinical Systems remediation for: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The necessary check instead is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

A forged policy document is rejected or quarantined and the agent cites only authorized versioned sources. This is evidence for a different corrective change: Validate trusted document provenance, restrict source updates, and record retrieval lineage before ingesting new context. That other change addresses: A question-answering agent indexes mutable policy documents without content verification, allowing poisoned text to contaminate answers. It does not validate the specific Northgate Clinical Systems remediation for: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The necessary check instead is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

Constrain each agent tool with separate scoped authorization and explicit approval for sensitive actions. This action could be suitable for a different engineering incident: An autonomous workflow agent can invoke billing exports using the same highly privileged identity it uses for ordinary summarization. It does not directly correct the reported Stonewell Payments failure: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The discriminating acceptance check here is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

Set data-minimizing storage and deletion policies across prompt, retrieval, logging, and model telemetry systems. This action could be suitable for a different engineering incident: A legal-assistance assistant stores personal prompts indefinitely although contractual retention limits require rapid deletion. It does not directly correct the reported Stonewell Payments failure: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The discriminating acceptance check here is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

Pin reviewed container images and dependencies, verify provenance signatures or digests, and scan for known risks. This action could be suitable for a different engineering incident: A team deploys a model package from an unsigned third-party image with dependencies downloaded at runtime from uncontrolled mirrors. It does not directly correct the reported Stonewell Payments failure: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The discriminating acceptance check here is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

A retention test confirms expired personal prompts are deleted while required non-sensitive audit markers remain. This is evidence for a different corrective change: Set data-minimizing storage and deletion policies across prompt, retrieval, logging, and model telemetry systems. That other change addresses: A legal-assistance assistant stores personal prompts indefinitely although contractual retention limits require rapid deletion. It does not validate the specific Stonewell Payments remediation for: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The necessary check instead is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

A tampered artifact is refused at release and the accepted image matches the approved supply-chain manifest. This is evidence for a different corrective change: Pin reviewed container images and dependencies, verify provenance signatures or digests, and scan for known risks. That other change addresses: A team deploys a model package from an unsigned third-party image with dependencies downloaded at runtime from uncontrolled mirrors. It does not validate the specific Stonewell Payments remediation for: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The necessary check instead is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

A harmless summary succeeds but a disallowed export tool call is rejected and logged. This is evidence for a different corrective change: Constrain each agent tool with separate scoped authorization and explicit approval for sensitive actions. That other change addresses: An autonomous workflow agent can invoke billing exports using the same highly privileged identity it uses for ordinary summarization. It does not validate the specific Stonewell Payments remediation for: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. The necessary check instead is: Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility.

Treat retrieved content as untrusted and enforce tool authorization, instruction hierarchy, and prompt-injection defenses. This action could be suitable for a different engineering incident: A retrieval-augmented support bot obeys a malicious instruction hidden inside a retrieved webpage to reveal internal prompts. It does not directly correct the reported Harbor Rail Logistics failure: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The discriminating acceptance check here is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

Measure group-sliced error and fairness metrics, investigate feature bias, and enforce an approved remediation process. This action could be suitable for a different engineering incident: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. It does not directly correct the reported Harbor Rail Logistics failure: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The discriminating acceptance check here is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

Use Secret Manager or a secured secret-injection workflow and revoke exposed credentials. This action could be suitable for a different engineering incident: A pipeline embeds production database passwords in plain text inside model-training container environment files committed to source control. It does not directly correct the reported Harbor Rail Logistics failure: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The discriminating acceptance check here is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility. This is evidence for a different corrective change: Measure group-sliced error and fairness metrics, investigate feature bias, and enforce an approved remediation process. That other change addresses: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. It does not validate the specific Harbor Rail Logistics remediation for: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The necessary check instead is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

A red-team retrieved document fails to induce prohibited disclosure or tool use while legitimate questions still work. This is evidence for a different corrective change: Treat retrieved content as untrusted and enforce tool authorization, instruction hierarchy, and prompt-injection defenses. That other change addresses: A retrieval-augmented support bot obeys a malicious instruction hidden inside a retrieved webpage to reveal internal prompts. It does not validate the specific Harbor Rail Logistics remediation for: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The necessary check instead is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

A repository scan finds no active plaintext secret and the authorized training task obtains it only at execution time. This is evidence for a different corrective change: Use Secret Manager or a secured secret-injection workflow and revoke exposed credentials. That other change addresses: A pipeline embeds production database passwords in plain text inside model-training container environment files committed to source control. It does not validate the specific Harbor Rail Logistics remediation for: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The necessary check instead is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

Measure group-sliced error and fairness metrics, investigate feature bias, and enforce an approved remediation process. This action could be suitable for a different engineering incident: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. It does not directly correct the reported Aster Pharma failure: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The discriminating acceptance check here is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

Apply task-appropriate safety filtering and refusal evaluation with thresholds explicitly covering prohibited response classes. This action could be suitable for a different engineering incident: A generative assistant returns disallowed harmful instructions because a high overall helpfulness score is the only release metric. It does not directly correct the reported Aster Pharma failure: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The discriminating acceptance check here is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

Use Secret Manager or a secured secret-injection workflow and revoke exposed credentials. This action could be suitable for a different engineering incident: A pipeline embeds production database passwords in plain text inside model-training container environment files committed to source control. It does not directly correct the reported Aster Pharma failure: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The discriminating acceptance check here is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

A reviewed unsafe-prompt suite elicits the required refusals while permitted requests remain useful. This is evidence for a different corrective change: Apply task-appropriate safety filtering and refusal evaluation with thresholds explicitly covering prohibited response classes. That other change addresses: A generative assistant returns disallowed harmful instructions because a high overall helpfulness score is the only release metric. It does not validate the specific Aster Pharma remediation for: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The necessary check instead is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

Held-out subgroup results meet the stated fairness guardrails without hiding deterioration in overall utility. This is evidence for a different corrective change: Measure group-sliced error and fairness metrics, investigate feature bias, and enforce an approved remediation process. That other change addresses: A hiring predictor has good total accuracy but systematically rejects qualified applicants from one audited group. It does not validate the specific Aster Pharma remediation for: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The necessary check instead is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

A repository scan finds no active plaintext secret and the authorized training task obtains it only at execution time. This is evidence for a different corrective change: Use Secret Manager or a secured secret-injection workflow and revoke exposed credentials. That other change addresses: A pipeline embeds production database passwords in plain text inside model-training container environment files committed to source control. It does not validate the specific Aster Pharma remediation for: A business team presents feature attribution values from an opaque model as mathematical proof that changing the top-ranked attribute will change an outcome. The necessary check instead is: The model card labels explanatory associations accurately and rejects unsupported causal conclusions.

Constrain each agent tool with separate scoped authorization and explicit approval for sensitive actions. This action could be suitable for a different engineering incident: An autonomous workflow agent can invoke billing exports using the same highly privileged identity it uses for ordinary summarization. It does not directly correct the reported Mercury Travel Tech failure: A trained model is saved in a broadly writable bucket where unrelated developers can replace weights without authorization. The discriminating acceptance check here is: A developer outside the release role cannot replace the artifact, while the expected digest loads successfully.

Evaluate threat-relevant adversarial and out-of-distribution inputs and deploy risk-based input checks or fallback handling. This action could be suitable for a different engineering incident: A public model endpoint is susceptible to adversarial image perturbations but its safety review tests only pristine images. It does not directly correct the reported Mercury Travel Tech failure: A trained model is saved in a broadly writable bucket where unrelated developers can replace weights without authorization. The discriminating acceptance check here is: A developer outside the release role cannot replace the artifact, while the expected digest loads successfully.

Restrict inference service access to its exact datasets and serving resources using narrowly scoped identities. This action could be suitable for a different engineering incident: A production inference identity can list all organization datasets although it only requires one approved feature view. It does not directly correct the reported Mercury Travel Tech failure: A trained model is saved in a broadly writable bucket where unrelated developers can replace weights without authorization. The discriminating acceptance check here is: A developer outside the release role cannot replace the artifact, while the expected digest loads successfully.

A controlled attack suite exposes fewer unsafe high-confidence predictions without unacceptable legitimate error. This is evidence for a different corrective change: Evaluate threat-relevant adversarial and out-of-distribution inputs and deploy risk-based input checks or fallback handling. That other change addresses: A public model endpoint is susceptible to adversarial image perturbations but its safety review tests only pristine images. It does not validate the specific Mercury Travel Tech remediation for: A trained model is saved in a broadly writable bucket where unrelated developers can replace weights without authorization. The necessary check instead is: A developer outside the release role cannot replace the artifact, while the expected digest loads successfully.

Authorized feature reads succeed and cross-team dataset access attempts are denied in the audit trail. This is evidence for a different corrective change: Restrict inference service access to its exact datasets and serving resources using narrowly scoped identities. That other change addresses: A production inference identity can list all organization datasets although it only requires one approved feature view. It does not validate the specific Mercury Travel Tech remediation for: A trained model is saved in a broadly writable bucket where unrelated developers can replace weights without authorization. The necessary check instead is: A developer outside the release role cannot replace the artifact, while the expected digest loads successfully.

A harmless summary succeeds but a disallowed export tool call is rejected and logged. This is evidence for a different corrective change: Constrain each agent tool with separate scoped authorization and explicit approval for sensitive actions. That other change addresses: An autonomous workflow agent can invoke billing exports using the same highly privileged identity it uses for ordinary summarization. It does not validate the specific Mercury Travel Tech remediation for: A trained model is saved in a broadly writable bucket where unrelated developers can replace weights without authorization. The necessary check instead is: A developer outside the release role cannot replace the artifact, while the expected digest loads successfully.