Index of every page on this site: llms.txt
All skills
jeremylongshore avatar

/adobe-policy-guardrails

@820dfc8
Run it yourself

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".

Use this Skill: https://skilld.dev/gh/jeremylongshore/tons-of-skills-marketplace/adobe-policy-guardrails

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈81 tokens for metadata: the name and description. ≈880 when used: this file. ≈823 more on demand in 1 file.

Description uses 4.0% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈323 characters, or 4.0%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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 — recheck dated Adobe sources before execution.
  • Treat observed tenant or product behavior as environment-specific evidence, never a universal Adobe guarantee.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill provides automated policy enforcement and guardrails for Adobe integrations, including credential scanning and content pre-screening. It identifies as having an attack surface for indirect prompt injection because it processes untrusted user prompts, but it follows security best practices by providing tools to detect and prevent credential exposure.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at 820dfc8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago
What it can do
Reads files Edits files
Modelinherit
argument-hint
<repository-or-service> <operations> <policy-owners>
version
1.8.0
author
Jeremy Longshore <jeremy@intentsolutions.io>
All 5 allowed tools
ReadGlobGrepWriteEdit
Other metadata
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

README badge

README badge for jeremylongshore/tons-of-skills-marketplace/adobe-policy-guardrails