- Home
- Skills
- DevOps & Cloud
- aws iam policy risk analyzer
More screenshots
Works with the AI Agents you already use
aws iam policy risk analyzer
Find privilege-escalation action combinations, Allow *, unrestricted PassRole and risky OIDC trust in IAM policy dumps — offline.
$12
aws iam policy risk analyzer
Example session with this skill installed
python3 scripts/iamrisk.py --authz examples/authz-mini.json --md iam-risk.md
- Read your context and instructions
- Compiled the aws iam policy
CRITICAL AdministratorAccess on ci-bot; HIGH PassRole+Lambda; HIGH GitHub OIDC without sub
Connects securely to your tools. The creator never sees your data.
About this skill
*Find privilege-escalation action combinations, Allow , unrestricted PassRole and risky OIDC trust in IAM policy dumps — offline.
Analyze AWS IAM policies and account authorization dumps offline for privilege-escalation action combinations (Rhino Labs methods), Allow * / Resource *, NotAction+Allow, unrestricted PassRole, public or cross-account role trust, and GitHub OIDC trust missing the sub claim. Reads aws iam get-account-authorization-details JSON or individual policy files and writes a severity-ranked report plus CSV. Use when someone asks "is this IAM policy safe?", "find privilege escalation in our account" or "review our GitHub OIDC role".
What it does
- Runs entirely offline in standard-library Python (no network, no credentials, writes only inside the working folder).
- Ships with examples, unit tests (run on Python 3.8 / 3.9 / 3.13) and a
references/sources.mdciting the official specs used. - Exit codes: 0 = clean / aligned, 1 = findings, 2 = bad input — ready for CI and agent loops.
Who it's for
Security-minded developers, MSPs, small-business IT, compliance leads and IR analysts who want a repeatable offline check their agent can run.
Not legal advice / limits
See the skill's references/sources.md and Known Limitations below. Compliance-flavored output is a draft for counsel, not a certification.
- Heuristic extractors (policy text, MFA column names, YAML subset) can miss unusual formats — always review the "settings/columns used" line.
- Specs are cited in
references/sources.md; anything marked unverified there is called out, not guessed. - Not a substitute for Access Analyzer, GuardDuty, a full disk image or a lawyer.
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 any payment.
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 month ago
Permissions
File Scopes