webPromedium
Lab 105 — WriteFlow — Indirect Prompt Injection via Document Analysis
hackadvisor
Task: AI-powered content management platform (WriteFlow) with a document analyzer whose fetch_reference tool makes server-side HTTP requests triggered by specific phrases in document content. Solution: craft document text with the trigger phrase pointing to localhost, port-scan to discover internal config service on port 3001, and exfiltrate secrets from /internal/config containing the flag.
$ ls tags/ techniques/
ssrfnodejsindirect_prompt_injectiondocument_analysisllmai_securityprompt_injectiondecoy_flaginternal_service_discoveryport_scanning
internal_service_enumerationssrf_via_ai_toolinternal_port_scanningindirect_prompt_injection_via_document_contenttrigger_phrase_exploitation
🔒
Permission denied (requires tier.pro)
Sign in to access full writeups
Sign in with GitHub to continue. No email required.
$sign in$ grep --similar
Similar writeups
- [web][Pro]Lab 104 — CloudOps Copilot — AI SSRF via Infrastructure Tool Abuse— hackadvisor
- [web][Pro]Lab 205 — DockForge — SSRF in Webhook Test Endpoint— hackadvisor
- [web][Pro]Lab 156 — IntegraFlow — Path Traversal via Double URL Encoding— hackadvisor
- [web][Pro]Lab 37 — WriteFlow — NoSQL Injection via Nested $where in Mongoose Populate— hackadvisor
- [web][Pro]Lab 102 — HireScreen — Indirect Prompt Injection via Resume Description— hackadvisor