AI Agent Threat Matrix
Matrix/Credential Harvest/T-3001
T-3001observed

System Prompt Credential Extraction

Extract credentials hardcoded or referenced in the agent's system prompt

Tactic

Credential Harvest (Stage 3)

Extract API keys, tokens, and credentials from agent context and connected services

Attack Class

RETROACTIVE-PRIV

Exploiting previously granted access or cached credentials to gain unauthorized capabilities

Evidence

observed

Confirmed in real-world production systems or internet-wide exposure assessments.

DVAA Validation

L1-02

Detection (HackMyAgent)

CRED-001CRED-002CRED-003CRED-004
npx hackmyagent secure --ci

Defense (OASB Controls)

OASB 5.1OASB 5.2OASB 5.3OASB 5.4OASB 5.5

How to Cite

AI Agent Threat Matrix T-3001 (System Prompt Credential Extraction). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-3001
← Back to Matrix