dotPilot: Skill for Codex

MCAF: Security Baseline

Trigger On

• a change has security impact but does not need a full separate AppSec exercise
• the work touches auth, secrets, trust boundaries, data flow, or pipeline permissions
• the team needs secure-default guidance before implementing

Value

• produce a concrete project delta: code, docs, config, tests, CI, or review artifact
• reduce ambiguity through explicit planning, verification, and final validation skills
• leave reusable project context so future tasks are faster and safer

Do Not Use For

• a full standalone threat-modeling engagement
• generic code review with no security surface

Inputs

• the changed boundary, data flow, or integration
• auth, secret, and permission model for the affected path
• current security docs, ADRs, or CI rules

Quick Start

1. Read the nearest AGENTS.md and confirm scope and constraints.
2. Run this skill's Workflow through the Ralph Loop until outcomes are acceptable.
3. Return the Required Result Format with concrete artifacts and verification evidence.

Workflow

1. Identify the security surface:
   • authn and authz
   • secrets
   • external inputs
   • storage and transport
   • pipeline permissions
2. Apply secure defaults and least privilege before adding behaviour.
3. If the change introduces a trust boundary, update or add an ADR and link the reasoning.
4. Pull the relevant security references, not the whole set.

Deliver

• security-aware design or implementation guidance
• updated security checkpoints in docs, ADRs, or CI
• the right threat-model references for the impacted area

Validate

• secrets are handled explicitly
• authn and authz assumptions are visible
• new trust boundaries are documented
• the change does not smuggle insecure defaults into the repo

Ralph Loop

Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.

1. Brainstorm first (mandatory):
   • analyze current state
   • define the problem, target outcome, constraints, and risks
   • generate options and think through trade-offs before committing
   • capture the recommended direction and open questions
2. Plan second (mandatory):
   • write a detailed execution plan from the chosen direction
   • list final validation skills to run at the end, with order and reason
3. Execute one planned step and produce a concrete delta.
4. Review the result and capture findings with actionable next fixes.
5. Apply fixes in small batches and rerun the relevant checks or review steps.
6. Update the plan after each iteration.
7. Repeat until outcomes are acceptable or only explicit exceptions remain.
8. If a dependency is missing, bootstrap it or return status: not_applicable with explicit reason and fallback path.