Credential Reuse
Reuse harvested credentials to access additional services and agents
Tactic
Lateral Movement (Stage 5)
Pivot from compromised agent to connected services or other agents
Attack Class
RETROACTIVE-PRIV
Exploiting previously granted access or cached credentials to gain unauthorized capabilities
Evidence
Confirmed in real-world production systems or internet-wide exposure assessments.
DVAA Validation
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
credential reuse
Honeypot Coverage (AgentPwn)
Not observable via content-side honeypot interaction. HackMyAgent or DVAA cover this where applicable.
Requires cross-system credential context that AgentPwn does not simulate.
Evidence Source Breakdown
Evidence Timeline
HMA check CRED-001 failed on cred-test
HMA check CRED-001 failed on cred-test
HMA check CRED-001 failed on cred-test
HMA check CRED-001 failed on soc-demo
HMA check CRED-001 failed on opena2a-cli
HMA check CRED-001 failed on cred-test
HMA check CRED-001 failed on cred-test
HMA check CRED-001 failed on cred-test
HMA check CRED-001 failed on cred-test
Detection (HackMyAgent)
npx hackmyagent secure --ciLive = check implemented in hackmyagent; queued = declared, not yet implementedDefense (OASB Controls)
How to Cite
AI Agent Threat Matrix T-5004 (Credential Reuse). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-5004