T-9005Adapted
Reputation Poisoning
Generate malicious or harmful outputs to damage the agent operator's reputation
Tactic
Impact · Stage 9
Modify data, deploy malicious code, or disrupt services
Attack class
ORG-SKILL-SPREAD
Propagating malicious capabilities across an organization's agent fleet through shared skills and registries
Evidence grade
AdaptedA well-understood traditional technique applied to the AI agent context.
DVAA validation
malicious output generation
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
Honeypot
AgentPwn coverage
In scope for honeypot observation; trap page or telemetry hook not yet built.
Eliciting reputation-damaging output via jailbreak tiers is adjacent; no dedicated fixture yet.
Detect
Detection · HackMyAgent
SUPPLY-001
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefend
Defense · OASB controls
Reference
How to cite
AI Agent Threat Matrix T-9005 (Reputation Poisoning). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-9005