T-7006ValidatedActive1 evidence record

PII Discovery

Discover and extract personally identifiable information from RAG stores and agent data sources

Tactic

Collection · Stage 7

Gather and stage data from databases, file systems, and APIs

Attack class

RAG-POISON

Injecting malicious content into retrieval-augmented generation data sources

Evidence grade
Validated

Reproduced in a controlled lab environment (DVAA) with documented steps.

DVAA validation

LegacyBot PII leak

Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.

Honeypot

AgentPwn coverage

Live
data-exfiltrationagentpwn.com/learn ↗

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.

Provenance

Evidence by source

HackMyAgent
1 record
Trail

Evidence timeline

HackMyAgent

HMA check RAG-002 failed on damn-vulnerable-ai-agent

Apr 22, 2026
Detect

Detection · HackMyAgent

Live4 live · 0 queued
RAG-001RAG-002RAG-003RAG-004
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declared
Defend

Defense · OASB controls

Live4 live · 0 queued
Live = documented at oasb.ai; queued = declared
Reference

How to cite

AI Agent Threat Matrix T-7006 (PII Discovery). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-7006