Skip to main content Início Criadores jeremylongshore tons-of-skills-marketplace adobe-policy-guardrails
adobe-policy-guardrails Implement Adobe-specific lint rules, CI policy checks, and runtime guardrails
covering credential scanning (p8_ patterns), Firefly content policy pre-screening,
PDF Services quota enforcement, and OAuth scope validation.
Trigger with phrases like "adobe policy", "adobe lint",
"adobe guardrails", "adobe eslint", "adobe content policy".
Ir para a instalação Skills Marketplace Descubra e explore skills de IA criadas pela comunidade.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Mostrar detalhes do prompt Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
npx skills add https://github.com/jeremylongshore/tons-of-skills-marketplace --skill adobe-policy-guardrailsO comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.
Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.
Baixar Zip Baixando... Mais deste repositório langchain-deploy-integration Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — with timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, and Secret Manager over .env. Use when prepping a first production deploy, debugging a stream that hangs behind a proxy, or diagnosing p99 latency spikes. Trigger with "langchain deploy", "langchain cloud run", "langchain vercel python", "langchain langserve", or "langchain docker".
langchain-langgraph-agents Build a correct LangGraph 1.0 ReAct agent with create_react_agent — typed tools, error propagation, recursion caps, and stop conditions that actually stop. Use when writing a first tool-calling agent, migrating from AgentExecutor or initialize_agent, or diagnosing an agent that loops on vague prompts. Trigger with "langgraph agent", "create_react_agent", "langgraph tool calling", "AgentExecutor migration", or "agent loop cost".
langchain-langgraph-human-in-loop Build LangGraph 1.0 human-in-the-loop approval flows with interrupt_before /
interrupt_after and Command(resume=...) — JSON-serializable state, clean
resume semantics, and UI wiring for approval decisions. Use when adding an
approval gate before an expensive tool call, wiring a Slack/web UI for agent
approvals, or debugging a graph that crashes on interrupt.
Trigger with "langgraph human in loop", "langgraph interrupt_before",
"langgraph approval flow", "Command resume", "langgraph HITL".
name adobe-policy-guardrails description Implement Adobe-specific lint rules, CI policy checks, and runtime guardrails
covering credential scanning (p8_ patterns), Firefly content policy pre-screening,
PDF Services quota enforcement, and OAuth scope validation.
Trigger with phrases like "adobe policy", "adobe lint",
"adobe guardrails", "adobe eslint", "adobe content policy".
allowed-tools Read, Write, Edit, Bash(npx:*) version 1.7.0 license MIT author Jeremy Longshore <jeremy@intentsolutions.io> tags ["saas","design","adobe"] compatibility Designed for Claude Code
Adobe Policy & Guardrails
Overview
Automated policy enforcement for Adobe integrations: credential pattern scanning (Adobe OAuth secrets use p8_ prefix), Firefly content policy pre-screening, PDF Services quota guardrails, and OAuth scope validation.
Prerequisites
ESLint configured in project
CI/CD pipeline (GitHub Actions)
Understanding of Adobe credential patterns
Instructions
Guardrail 1: Adobe Credential Pattern Scanner
Adobe OAuth Server-to-Server secrets follow the p8_ prefix pattern:
name: Adobe Security Scan
on: [push , pull_request ]
jobs:
credential-scan:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Scan for Adobe credential patterns
run: |
EXIT_CODE=0
if grep -rE "p8_[A-Za-z0-9_-]{20,}" --include="*.ts" --include="*.js" --include="*.py" --include="*.json" --include="*.yaml" --include="*.yml" . 2 >/dev/null | grep -v
node_modules
|
grep
-v
'.git'
;
then
echo
"::error::Adobe client_secret pattern (p8_) found in source code"
EXIT_CODE=1
fi
if
grep
-rE
"eyJ[A-Za-z0-9_-]{100,}\.[A-Za-z0-9_-]{100,}"
--include="*.ts"
--include="*.js"
.
2
>/dev/null
|
grep
-v
node_modules
|
grep
-v
'.git'
|
grep
-v
'\.test\.'
|
grep
-v
'__mock'
;
then
echo
"::warning::Potential Adobe access token found in source (may be test fixture)"
fi
if
grep
-rE
"[A-F0-9]{24}@AdobeOrg"
--include="*.ts"
--include="*.js"
--include="*.json"
.
2
>/dev/null
|
grep
-v
node_modules
|
grep
-v
'.git'
|
grep
-v
'.env.example'
;
then
echo
"::warning::Adobe Org ID found in source — consider using env var"
fi
exit
$EXIT_CODE
Guardrail 2: Firefly Content Policy Pre-Screener
interface ContentPolicyResult {
allowed : boolean ;
violations : string [];
suggestions : string [];
}
const CONTENT_RULES = [
{
name : 'real-people' ,
pattern : /\b(photo of|portrait of|picture of)\s+(a\s+)?(real|actual|specific)\s+(person|man|woman|child)/i ,
message : 'Firefly cannot generate images of specific real people' ,
suggestion : 'Use generic descriptions like "a professional in a business suit"' ,
},
{
name : 'trademarks' ,
pattern : /\b(nike|adidas|apple|google|microsoft|disney|marvel|coca.?cola|pepsi|starbucks|mcdonalds)\b/i ,
message : 'Firefly will reject prompts containing brand trademarks' ,
suggestion : 'Use generic descriptions like "athletic shoes" or "tech company logo style"' ,
},
{
name : 'explicit-content' ,
pattern : /\b(nude|naked|explicit|pornograph|gore|violent|bloody|graphic death)\b/i ,
message : 'Firefly rejects explicit or violent content' ,
suggestion : 'Use appropriate imagery descriptions' ,
},
{
name : 'celebrity' ,
pattern : /\b(celebrity|famous|actor|actress|politician|president|singer|musician)\s+(name|like|resembling)/i ,
message : 'Firefly cannot generate images of identifiable celebrities' ,
suggestion : 'Describe the style or aesthetic without naming individuals' ,
},
];
export function screenFireflyPrompt (prompt : string ContentPolicyResult {
const violations : string [] = [];
const suggestions : string [] = [];
for (const rule of CONTENT_RULES ) {
if (rule.pattern .test (prompt)) {
violations.push (`[${rule.name} ] ${rule.message} ` );
suggestions.push (rule.suggestion );
}
}
return {
allowed : violations.length === 0 ,
violations,
suggestions,
};
}
export function guardFireflyPrompt (prompt : string void {
const result = screenFireflyPrompt (prompt);
if (!result.allowed ) {
throw new Error (
`Firefly content policy pre-check failed:\n` +
result.violations .join ('\n' ) +
'\n\nSuggestions:\n' +
result.suggestions .join ('\n' )
);
}
}
Guardrail 3: PDF Services Quota Enforcement
class PdfQuotaGuard {
private monthlyLimit : number ;
private transactionsUsed : number = 0 ;
private monthStart : Date ;
constructor (tier : 'free' | 'paid' = 'free' this .monthlyLimit = tier === 'free' ? 500 : Infinity ;
this .monthStart = new Date (new Date ().getFullYear (), new Date ().getMonth (), 1 );
}
check (): { allowed : boolean ; remaining : number ; warning : boolean } {
const now = new Date ();
if (now.getMonth () !== this .monthStart .getMonth ()) {
this .transactionsUsed = 0 ;
this .monthStart = new Date (now.getFullYear (), now.getMonth (), 1 );
}
const remaining = this .monthlyLimit - this .transactionsUsed ;
return {
allowed : remaining > 0 ,
remaining,
warning : remaining < this .monthlyLimit * 0.2 ,
};
}
record (): void {
const status = this .check ();
if (!status.allowed ) {
throw new Error (`PDF Services quota exhausted (${this .monthlyLimit} transactions/month)` );
}
this .transactionsUsed ++;
if (status.warning ) {
console .warn (`PDF Services: ${status.remaining - 1 } transactions remaining this month` );
}
}
}
export const pdfQuota = new PdfQuotaGuard (
process.env .ADOBE_PDF_TIER === 'paid' ? 'paid' : 'free'
);
Guardrail 4: OAuth Scope Validation
function validateAdobeScopes (scopes : string , environment : string void {
const scopeList = scopes.split (',' ).map (s =>trim ());
if (environment === 'development' ) {
const prodOnlyScopes = ['ff_apis' ];
const violations = scopeList.filter (s =>includes (s));
if (violations.length > 0 ) {
console .warn (`Adobe scope warning: ${violations.join(', ' )} should not be in development` );
}
}
const required = ['openid' , 'AdobeID' ];
const missing = required.filter (s =>includes (s));
if (missing.length > 0 ) {
throw new Error (`Adobe required scopes missing: ${missing.join(', ' )} ` );
}
}
Guardrail 5: Runtime Operation Guard
const BLOCKED_IN_PROD : Record <string , string > = {
'delete-all-assets' : 'Mass deletion blocked in production' ,
'reset-quota-counter' : 'Quota reset blocked in production' ,
'use-test-credentials' : 'Test credentials blocked in production' ,
};
function guardAdobeOperation (operation : string void {
const isProd = process.env .NODE_ENV === 'production' ;
if (isProd && BLOCKED_IN_PROD [operation]) {
throw new Error (`BLOCKED: ${BLOCKED_IN_PROD[operation]} ` );
}
}
Output
CI secret scanning for Adobe credential patterns (p8_, JWTs, Org IDs)
Firefly prompt pre-screening avoiding wasted credits on policy violations
PDF Services quota enforcement with monthly tracking
OAuth scope validation per environment
Runtime operation guards for production safety
Error Handling Issue Cause Solution Secret scan false positive Test fixture contains pattern Exclude test dirs from scan Prompt wrongly rejected Pattern too broad Refine regex; allow legitimate uses Quota counter reset Server restart Persist counter in Redis/DB Scope validation fails Wrong env var Check NODE_ENV and ADOBE_SCOPES
Examples Start with the smallest applicable command or code example already provided in this guide, using a non-production Adobe environment and credentials. Confirm the documented response or validation result before applying the pattern to production.
Resources
Next Steps For architecture blueprints, see adobe-architecture-variants.
