Skip to main content
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".
설치로 이동 Skills Marketplace 커뮤니티가 만든 AI 스킬을 발견하고 탐색하세요.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
직접 명령은 검토 Prompt를 거치지 않습니다. 실행하기 전에 소스를 확인하세요.
npx skills add https://github.com/jeremylongshore/claude-code-plugins-plus-skills --skill adobe-policy-guardrails명령은 한 줄로 유지됩니다. 복사하기 전에 가로로 스크롤해 전체 내용을 확인하세요.
로컬 사본을 원하시나요? SkillsMP에서 현재 제공할 수 있는 파일을 다운로드하세요.
Zip 다운로드 다운로드 중... jeremylongshore
jeremylongshore/claude-code-plugins-plus-skills
GitHub 저장소 열기 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 1.6.0 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
Resources
Next Steps For architecture blueprints, see adobe-architecture-variants.
