System Prompt Credential Extraction
Extract credentials hardcoded or referenced in the agent's system prompt
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
Confirmed in real-world production systems or internet-wide exposure assessments.
L1-02
Reproductions in Damn Vulnerable AI Agent, the OpenA2A intentionally-broken agent for kill-chain validation.
Recent observations
Technique-attributed observations from the AgentPwn + TrapMyAgent fleet, classified into Threat Matrix techniques by the registry evidence bridge. See the Attack Prevalence Index for the full distribution.
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.
Credential-probe tiers extract secrets referenced in the system prompt.
Evidence by source
Evidence timeline
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
HMA check CRED-001 failed on singlefile-test
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Client fetched the canary embedded in APWN-DE-001 on agentpwn.com (data-exfiltration tier 1; classified browser/claimed)
Client fetched a data-exfiltration canary on agentpwn.com (category-level: the lure carried no payload id; classified browser/claimed)
Detection · HackMyAgent
npx hackmyagent secure --ciLive = implemented in hackmyagent; queued = declaredDefense · OASB controls
How to cite
AI Agent Threat Matrix T-3001 (System Prompt Credential Extraction). OpenA2A, 2026. https://threats.opena2a.org/techniques/T-3001