Matrix/Impact/T-9005
T-9005adaptedactive7 evidence records

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

adapted

Well-understood traditional technique applied to the AI agent context.

DVAA Validation

Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.

malicious output generation

Honeypot Coverage (AgentPwn)

Queued

In scope for honeypot observation; trap page or telemetry hook not yet built.

Evidence Source Breakdown

HMA
7 records

Evidence Timeline

HMA

HMA check SUPPLY-001 failed on fake-vulnerable-agent

Apr 29, 2026
HMA

HMA check SUPPLY-001 failed on fake-vulnerable-agent

Apr 29, 2026
HMA

HMA check SUPPLY-001 failed on opena2a/code-review-skill

Apr 27, 2026
HMA

HMA check SUPPLY-001 failed on opena2a/code-review-skill

Apr 27, 2026
HMA

HMA check SUPPLY-001 failed on fake-vulnerable-agent

Apr 22, 2026
HMA

HMA check SUPPLY-001 failed on damn-vulnerable-ai-agent

Apr 22, 2026
HMA

HMA check SUPPLY-001 failed on hackmyagent-release-test-vplv

Apr 13, 2026

Detection (HackMyAgent)

Live1 live · 0 queued
SUPPLY-001
npx hackmyagent secure --ciLive = check implemented in hackmyagent; queued = declared, not yet implemented

Defense (OASB Controls)

Live5 live · 4 queued
OASB 6.1OASB 6.2OASB 6.3OASB 6.4OASB 6.5OASB 11.1OASB 11.2OASB 11.3OASB 11.4
Live = documented at oasb.ai; queued = declared, not yet documented

How to Cite

AI Agent Threat Matrix T-9005 (Reputation Poisoning). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-9005