PII Discovery
Discover and extract personally identifiable information from RAG stores and agent data sources
Collection · Stage 7
Gather and stage data from databases, file systems, and APIs
RAG-POISON
Injecting malicious content into retrieval-augmented generation data sources
Reproduced in a controlled lab environment (DVAA) with documented steps.
LegacyBot PII leak
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
AgentPwn coverage
An AgentPwn trap page produces a payload tagged with this technique class. Following the AgentPwn taxonomy of trap pages shows what an agent encounters.
Sector trap pages (/trap/medical-records, /trap/legal-documents, /trap/customer-portal, /trap/sec-filing) bait PII collection.
Evidence by source
Evidence timeline
HMA check RAG-002 failed on damn-vulnerable-ai-agent
Detection · HackMyAgent
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefense · OASB controls
How to cite
AI Agent Threat Matrix T-7006 (PII Discovery). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-7006