Govern what reaches a workspace.

Review threats at the gate that can address them. Keep evidence linked to the release and give workspaces control over the tiers they accept.

Threats and controls

Scroll horizontally to see the full comparison.

ThreatReview or controlGate
Untrusted instructionsReview instruction contents and declared behaviorScan
Undeclared accessReview tool use and sandbox observationsScan
Incomplete bundle analysisReview the full package and escalate gapsScan
Incorrect outputFunctional and adversarial tests for declared failure modesTest
RegressionCompare behavior with the previous approved versionTest
Dependency driftRe-test when a model, tool, or test case changesContinuous
Changes after approvalBind evidence and signature to a content hashSign
Version driftInstall an exact immutable releasePublish
Unreviewed community releasesAllow only workspace-approved trust tiersInstall
Misuse during executionApply runtime permissions and decision boundariesRuntime

Trust tiers and evidence

Scroll horizontally to see the full comparison.

ControlOfficialVerified PartnerCommunity
Publisher signaturePlatform-signedAttested partner keyPublisher signature
Workspace eligibilityRegulated defaultWorkspace opt-inOff by default
Review pathArchitecture review and full evaluator suitePartner review and evaluator suiteCatalog review and scanning
Deprecation12-month noticeStandard noticePublisher-managed

Operating the registry

  • Workspace privacy

    Discuss private distribution and access requirements before publishing business-specific skills.

  • Deployment requirements

    Review hosted, customer-cloud, and on-premises requirements with the team.

  • Audit evidence

    Use release records to connect scans, evaluations, signatures, and installation history.

  • Report a skill

    Open the relevant listing and use its reporting controls to raise a concern.

    Browse the catalog

Governance across your agent estate

Review wider agent risk and compliance controls with AgentGRC.