T-9003Observed1 evidence record
Malicious Code Deployment
Deploy malicious code or backdoors through agent code execution capabilities
Tactic
Impact · Stage 9
Modify data, deploy malicious code, or disrupt services
Attack class
HEARTBEAT-RCE
Exploiting scheduled task or heartbeat mechanisms to achieve persistent code execution
Evidence grade
ObservedConfirmed in real-world production systems or internet-wide exposure assessments.
DVAA validation
backdoor deployment
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
Honeypot
AgentPwn coverage
Not observable via content-side honeypot interaction. HackMyAgent or DVAA cover this where applicable.
No code-execution path on the honeypot; instruct-only, not observable.
Provenance
Evidence by source
HackMyAgent
1 record
Trail
Evidence timeline
HackMyAgent
HMA check SUPPLY-001 failed on damn-vulnerable-ai-agent
Apr 22, 2026
Detect
Detection · HackMyAgent
SUPPLY-001HEARTBEAT-001
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefend
Defense · OASB controls
Reference
How to cite
AI Agent Threat Matrix T-9003 (Malicious Code Deployment). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-9003