Context Window Credential Leak
Exploit context window contents to leak credentials that were previously processed by the agent
Credential Harvest · Stage 3
Extract API keys, tokens, and credentials from agent context and connected services
RETROACTIVE-PRIV
Exploiting previously granted access or cached credentials to gain unauthorized capabilities
Reproduced in a controlled lab environment (DVAA) with documented steps.
LegacyBot credential leak
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
AgentPwn coverage
An AgentPwn trap page produces a payload tagged with this technique class. Following the AgentPwn taxonomy of trap pages shows what an agent encounters.
Context-window tiers leak credentials retained in the active window.
Evidence by source
Evidence timeline
HMA check CRED-001 failed on cred-test
HMA check CRED-001 failed on cred-test
HMA check AGENT-CRED-001 failed on ai-trust
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
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
HMA check AGENT-CRED-001 failed on triggerdotdev/trigger.dev
HMA check AGENT-CRED-001 failed on @khanglvm/jira-mcp
HMA check AGENT-CRED-001 failed on nwiizo/tfmcp
HMA check AGENT-CRED-001 failed on saidsurucu/borsa-mcp
Detection · HackMyAgent
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefense · OASB controls
How to cite
AI Agent Threat Matrix T-3006 (Context Window Credential Leak). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-3006