T-9001Validated1 evidence record
Data Manipulation
Modify, corrupt, or delete data in databases and file systems via agent tools
Tactic
Impact · Stage 9
Modify data, deploy malicious code, or disrupt services
Attack class
CODE-INJECTION
Injecting and executing arbitrary code through SQL injection, command injection, or code generation
Evidence grade
ValidatedReproduced in a controlled lab environment (DVAA) with documented steps.
DVAA validation
ToolBot write_file, DataBot SQL
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.
Destructive data manipulation needs write tooling; the benevolent honeypot never stages it.
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-001INTEGRITY-001
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefend
Defense · OASB controls
Reference
How to cite
AI Agent Threat Matrix T-9001 (Data Manipulation). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-9001