Works with the AI Agents you already use
Srednoff AWS IAM Least-Privilege Reviewer
This is a read-only review workflow, not a cloud discovery service, policy evaluation engine or automatic permission remover; Azure and GCP semantics are not implemented.
$9.99
Srednoff AWS IAM Least-Privilege Reviewer
Example session with this skill installed
Review our sanitized AWS human and service-role grants against the named task inventory.
- Read your context and instructions
- Compiled the srednoff aws iam
Expected report shape, not a completed real audit: Executive Summary; AWS Scope And Revision; Principal And Trust Inventory
Connects securely to your tools. The creator never sees your data.
About this skill
Srednoff AWS IAM Least-Privilege Reviewer
One-Line Outcome
Produce an AWS-specific principal-to-task privilege matrix and approval-gated reduction proposal from supplied exports. This is a read-only review workflow, not a cloud discovery service, policy evaluation engine or automatic permission remover; Azure and GCP semantics are not implemented.
Short Description
Role names and last-used summaries hide resource grants, trust relationships and recovery duties; deleting apparently unused permissions can stop legitimate operations.
Problem It Solves
Role names and last-used summaries hide resource grants, trust relationships and recovery duties; deleting apparently unused permissions can stop legitimate operations.
Cloud account security owner: one named provider's supplied identity/role/resource/trust policy inventory, required-versus-granted privilege matrix and staged reduction proposal.
What You Get
- Executive Summary
- AWS Scope And Revision
- Principal And Trust Inventory
- Current / Required / Excess Privilege Matrix
- Policy Evaluation Assumptions
- Cross-Service Authority Paths
- Evidence Reviewed
- Threat Model
- Findings
- Critical Findings
- Quick Wins
- Prioritized Remediation Plan
- Missing Evidence
- Unknowns
- Residual Risk
- Verification Checklist
- Rollback / Compatibility Risk
How It Works
- Pin AWS scope and evidence revision; reject a provider-neutral effective-access verdict. Mark unsupported provider requests for a separate provider-specific review.
- Inventory human users and group inheritance separately from service roles, federated sessions and application service-account mappings. A machine identity label is not an AWS policy type.
- Map each principal to required business tasks and exceptional backup, restore, migration and emergency duties. Record an owner for every retained permission.
- Build a granted-policy ledger including inline/managed attachments, resource grants, boundary/session restrictions and applicable organization policies. Missing inherited evidence leaves affected decisions UNKNOWN.
- For each sampled action/resource/context, explain the AWS evaluation path, explicit denies and same-account versus cross-account differences; do not flatten all policy types into one union or intersection.
- Review wildcard actions/resources and admin grants against actual action resource-scoping support and task needs. Record grant breadth separately from credible effective reach.
- Trace role trust into who can assume the role, then the permissions available after assumption. Review human federation and temporary-session custody without issuing or inspecting tokens.
- Trace machine and cross-service authority: role passing plus service create/update rights, trusted service principal and supported source constraints. Evaluate confused-deputy conditions for the named integration.
- Inspect resource-policy grants to users, roles and sessions with their distinct boundary semantics. Check tag/condition inputs and who can change them; external IDs are context bindings, not secrets or universal service conditions.
- Reconcile activity with known collection windows, regions, services and seasonal tasks. Treat policy-generation output as a candidate, never proof unused permissions are dispensable.
- Draft a minimal reduction set with affected tasks, owner, compatibility risk and approval boundary. Preserve an independently reviewed recovery path; do not attach policies or revoke sessions.
- Specify disconnected fixture decisions and a separately authorized non-production canary for allowed tasks and forbidden actions. Deliver findings, unresolved paths and retest criteria; all unrun tests remain NOT_EXECUTED.
Best For
Cloud account security owners reviewing supplied AWS IAM evidence before a staged privilege reduction
Example Tasks
- Review our sanitized AWS human and service-role grants against the named task inventory.
- Explain whether this same-account role-session resource grant is actually bounded.
- Plan a staged AWS permission reduction without applying policies.
- Review a role-passing cross-service path from supplied policies.
Inputs
- Authorized AWS account aliases, partition, environment, export timestamp and candidate infrastructure revision; no account connection or credentials.
- Sanitized users, groups, machine identities, roles, attachments, inline policies, resource policies and trust policies, preserving structural relationships.
- Applicable organization SCP/RCP ancestry, permissions boundaries, session-policy context, policy versions and condition inputs, or explicit missing markers.
- Owner-approved task inventory: action, resource, actor, frequency, dependencies, emergency duties and expected success/denial; redacted activity coverage metadata.
Outputs
- Executive Summary
- AWS Scope And Revision
- Principal And Trust Inventory
- Current / Required / Excess Privilege Matrix
- Policy Evaluation Assumptions
- Cross-Service Authority Paths
- Evidence Reviewed
- Threat Model
- Findings
- Critical Findings
- Quick Wins
- Prioritized Remediation Plan
- Missing Evidence
- Unknowns
- Residual Risk
- Verification Checklist
- Rollback / Compatibility Risk
Permissions
Read-only review of owner-supplied artifacts by default. Report file writes, shell/local fixture execution and official documentation lookup are optional, require available tools and their explicit scope. No live credentials are requested.
Compatibility
Standalone workflow, no Srednoff OS dependency. Codex evidence is synthetic entrypoint text only when recorded below. Claude Code, Cursor and actual buyer-runtime task delivery remain UNTESTED. Provider/platform-specific contracts must be refreshed for the installed version.
Limitations
This is an instruction/evidence workflow, not a hosted security service, persistent enforcement engine, production certification or business guarantee. The optional Python helper checks supplied claims, not underlying source artifacts. Agensi delivery is agent-only: do not save/export proprietary skill files to run local helpers; disclose NOT_EXECUTED where execution is unavailable.
Validation Transparency
Offline evidence-precheck status: PASS. Authored synthetic text-response cases: 24/24, status PASS. This is not independent security testing, complete artifact inspection or proof of deployment safety. Exact-text hashes and attempts are retained separately.
License And Publisher
Commercial License 1.0 covers original new expression; historical MIT and third-party rights remain unchanged. Mandatory marketplace conditions prevail. Publisher: Ivan Srednoff / Srednoff.Agency. No proprietary source resale or off-platform paid upsell is included.
FAQ
What is different from a generic security request? Cloud account security owner: one named provider's supplied identity/role/resource/trust policy inventory, required-versus-granted privilege matrix and staged reduction proposal. No universal AWS/Azure/GCP compatibility, live IAM discovery, applied permission removal, agent tool policy or cluster workload audit.
Does it change production automatically? No. Audit/design is the default; changes, secret rotation, IAM, network probes and financial actions need separate explicit authorization.
Are the examples real incidents? No. They are synthetic DEMO DATA.
Is this a certification or guaranteed protection? No. Evidence gaps, residual risk and unexecuted tests remain explicit.
Can I use project-specific reports for clients? Yes under the included license; proprietary workflow source is not a client deliverable.
Version
1.0.0
Release Notes
Initial scoped security workflow with domain decision rules, evidence requirements, synthetic examples, regression cases and explicit authorization/runtime limits. No production/customer outcome is claimed.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
This is an instruction/evidence workflow, not a hosted security service, persistent enforcement engine, production certification or business guarantee. The optional Python helper checks supplied claims, not underlying source artifacts. Agensi delivery is agent-only: do not save/export proprietary skill files to run local helpers; disclose NOT_EXECUTED where execution is unavailable.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 day ago
Nothing to install. It runs in your AI agent.
- Optional
Python 3
No external account, API key or Srednoff OS installation is required. Supply authorized sanitized task evidence. Owner-authorized project inspection tools where available.