Use Case

Gate AI agents before they take real actions.

Agent workflows introduce approval, tool, memory, and handoff risks. ShakerScan tests those behaviors and records a release decision.

Sample gate decision

needs_approval

Approval bypass risk requires review

The agent attempted a privileged action after ambiguous user instructions. Policy requires a reviewer to approve or reject the deployment.

agent target:support-agent-workflow
tool scope:ticket.read, ticket.draft
approval rule:human approval before write
transcript evidence:privileged action attempted
1

Connect an agent API, trace, or workflow target.

2

Run agent-abuse probes focused on tools, approvals, memory, and handoffs.

3

Review evidence and policy rationale.

4

Require allow or scoped approval before deployment.

Why ShakerScan

The output is a release control, not just a report.

ShakerScan is built around release evidence: a tested target, a policy result, a verifier command, and an approval path when risk needs human review.

Signed evidence

Evidence hashes and AI Gate attestations bind the decision to the target, environment, policy, probe pack, and release scope when signing is configured.

CI-verifiable decision

GitHub Actions or the shakerscan CLI can verify that the decision matches the expected repo, commit, branch, environment, target, policy, and evidence hash.

Approval workflow

When an eligible workflow is approved, scoped approval tokens record the reason, audience, expiry, and decision path instead of bypassing the gate silently.

Checklist

Agent gate checklist

Map tools and privileged actions before testing.

Test approval bypass, tool result injection, memory poisoning, and handoff context.

Use read-only or sandbox credentials for first runs.

Require approval tokens for risky exceptions.

Limitations

What this page does not claim

ShakerScan does not replace human security review, threat modeling, or a scoped penetration test.

AI Gate decisions depend on the configured target, probe pack, policy, scan profile, and available evidence.

Production targets require authorization, safe scope, rate limits, and operational approval.

FAQ

Is ShakerScan an AI pentesting replacement?

No. ShakerScan is a verifiable security gate for release workflows. It complements deeper manual testing by producing repeatable runtime evidence and CI-verifiable allow, block, or needs_approval decisions.

Can ShakerScan scan any target?

No. Targets must be owned by the customer or explicitly authorized. Production scans should use safe profiles, rate limits, and defined scope.