iam-security-advisor SKILL.md skillA
iam-security-advisor from d-padmanabhan/agent-engineering-handbook is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add d-padmanabhan/agent-engineering-handbook/iam-security-advisor@git:20260825.bf1c995Pins git:20260825.bf1c995 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- d-padmanabhan/agent-engineering-handbook
- Path
skills/iam-security-advisor/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260825.bf1c995, committed Aug 25, 2026
- First version recorded
- Jul 19, 2026
- Size
- 10,723 bytes
- Repository stars
- 20
- License
- MIT
Principal-level IAM and security architecture advisor for identity protocols, IGA, PKI, PAM, secrets delivery, delegated access, and non-human identity. Use for architecture decisions, protocol deep dives, design reviews, threat models, or mentoring involving OAuth, OIDC, SAML, SCIM, mTLS, certificates, workload identity, Cross App Access, XAA, ID-JAG, agent-on-behalf-of-user flows, or privileged access.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# IAM Security Advisor Use this skill to produce decisive, evidence-based IAM and security architecture guidance. It complements: - [Identity and authentication rule](../../rules/315-iam.mdc) - [Zero Trust rule](../../rules/316-zero-trust.mdc) - [Workload identity rule](../../rules/318-workload-identity.mdc) - [AWS IAM rule](../../rules/412-aws-iam.mdc) Do not use it as a substitute for vendor-specific implementation documentation. ## Operating principles 1. Prefer reversible, least-privilege designs and short-lived credentials. 2. State assumptions and still provide a useful answer unless missing information blocks a safe decision. 3. Compare meaningful options, then recommend one. Do not stop at "it depends." 4. Name the attack path, failure mode, blast radius, and operational cost. 5. Separate identity, authorization, secrets, network, artifact integrity, audit, and recovery controls. 6. Verify current standards and vendor behavior before relying on exact identifiers, defaults, or features. ## Untrusted Evidence and Credential Safety …
Read the whole file at its exact version.
How to install
mdr add d-padmanabhan/agent-engineering-handbook/iam-security-advisor@sha256:ad1b3fc3097a9ac1The line at the top of this page pins the label git:20260825.bf1c995, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_qgu3popwjuoatkx2)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 19, 2026 and Aug 25, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260825.bf1c995 latest | 2026-08-25 | bf1c995 | 10,723 B | A | view · diff |
| git:20260824.a419591 | 2026-08-24 | a419591 | 10,725 B | A | view · diff |
| git:20260819.d23bb73 | 2026-08-19 | d23bb73 | 10,729 B | A | view · diff |
| git:20260814.d4970b5 | 2026-08-14 | d4970b5 | 10,779 B | A | view · diff |
| git:20260719.0b77fec | 2026-07-19 | 0b77fec | 9,364 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10723 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
d-padmanabhan/agent-engineering-handbook · 20 stars · license MIT · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_qgu3popwjuoatkx2 GET https://markdownregistry.com/api/v1/resolve?ref=d-padmanabhan/agent-engineering-handbook/iam-security-advisor GET https://markdownregistry.com/api/v1/blob/ad1b3fc3097a9ac1876076c9f84992df69fc603e21636300b460014660f2df89
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.