---
name: adobe-policy-guardrails
description: >-
  Analyze and enforce repository, runtime, data, spend, endpoint, and approval guardrails without guessing secret formats or content-policy rules. Use when the task requires adobe policy and execution guardrails. Trigger with "Adobe guardrails", "block unsafe Adobe calls", or "Adobe policy checks".
allowed-tools: Read,Glob,Grep,Write,Edit
argument-hint: "<repository-or-service> <operations> <policy-owners>"
version: 1.8.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags: [ saas, adobe, guardrails ]
model: inherit
effort: high
compatibility: "Designed for Claude Code; live Adobe actions require network access, appropriate entitlement and authentication, and explicit approval"
title: adobe-policy-guardrails
canonical_url: https://skilld.dev/gh/jeremylongshore/tons-of-skills-marketplace/adobe-policy-guardrails
last_updated: 2026-10-07T06:06:28.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [references/official-docs.md](https://skilld.dev/api/skills-raw/jeremylongshore/tons-of-skills-marketplace/adobe-policy-guardrails/references/official-docs.md).
>
> If the user asked to install this Skill, run `npx skilld install jeremylongshore/tons-of-skills-marketplace/adobe-policy-guardrails`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/adobe-policy-guardrails`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/jeremylongshore/tons-of-skills-marketplace/adobe-policy-guardrails) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/adobe-policy-guardrails`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/adobe-policy-guardrails --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/adobe-policy-guardrails --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Adobe Policy and Execution Guardrails

## Overview

Analyze and enforce repository, runtime, data, spend, endpoint, and approval guardrails without guessing secret formats or content-policy rules. This workflow produces a reviewable artifact and evidence before any live side effect.

## Prerequisites

- Current first-party Adobe documentation for every selected service, API version, auth flow, limit, and lifecycle.
- Named product, identity, security, data, budget, release, and operations owners appropriate to the scope.
- Synthetic or approved non-production fixtures with secret and content canaries.

## Current Contract

Guardrails derive from current service docs and local policy: approved auth flows, hosts/versions, scopes/profiles, schemas, storage domains, budgets, data classes, and approval boundaries. Secret prefixes and prompt regexes are not authoritative security or content-policy controls. Recheck the dated evidence map before relying on mutable product behavior.

## Authentication

Use mature secret scanners plus entropy/context rules and provider revocation procedures. Runtime authorization evaluates credential binding, entitlement, resource, operation, and approval.

## Instructions

1. Inventory all Adobe calls, credentials, endpoints, versions, payload classes, storage URLs, retries, jobs, events, and destructive operations.
2. Create allowlists for current hosts/versions/services and denylists for JWT, /sensei/cutout, and retired Lightroom Firefly Services.
3. Validate configuration/request/response schemas and redact tokens, signed URLs, prompts, and customer content.
4. Enforce data-purpose, owner, budget, concurrency, idempotency, and approval tokens before side effects.
5. Route Adobe policy outcomes to a human-readable denial path; never silently rewrite prompts or broaden scopes.
6. Test bypasses, stale docs, false positives, emergency disablement, exception expiry, and audit receipts.

## Tool Discipline

Use Read, Glob, and Grep to inspect current documentation, configuration, code, fixtures, and evidence. Use Write and Edit only for approved repository artifacts. Skill invocation alone does not authorize network access, credentials, Adobe content, consent, uploads, generation, spend, deployment, registration changes, replay, cancellation, or deletion.

## Approval Boundaries

Security/product/data/budget owners approve policy and exceptions. Generation, upload, deploy, webhook change, cancellation, replay, and deletion remain independently approved actions.

## Error Handling

- Do not claim Adobe secrets always have a specific prefix.
- Do not claim local regexes predict Firefly policy decisions.
- Fail closed when endpoint/version or approval evidence is unknown.

## Output

Return policy sources, allow/deny rules, enforcement points, test corpus, exceptions, receipts, drift monitor, and owners. Mark assumptions, observed environment behavior, owners, evidence dates, and unresolved gaps explicitly.

## Examples

- Block /sensei/cutout before network execution.
- Detect a signed URL in a log fixture and fail the gate.

## Validation

Exercise and record expected and observed results for:

- obsolete route
- unknown host
- secret leak
- policy outcome
- budget ceiling
- expired exception

## Resources

- [Current first-party evidence map](https://skilld.dev/api/skills-raw/jeremylongshore/tons-of-skills-marketplace/adobe-policy-guardrails/references/official-docs.md) — recheck dated Adobe sources before execution.
- Treat observed tenant or product behavior as environment-specific evidence, never a universal Adobe guarantee.
