Data ExfiltrationTier 1critical
Data Exfiltration: Credential Probe
Tricks to extract credentials, PII, or system information
Data exfiltration attacks trick AI agents into revealing sensitive information: credentials, system prompts, conversation history, or user data. These attacks exploit the agent's willingness to be helpful.
Attack Details
- Attack ID
- APWN-DE-001
- HMA Check
- CRED-001
- Delivery Methods
- html-comment
- CWE
- CWE-798
- OASB Control
- 5.1
- Severity
- critical
Remediation
If your AI agent is vulnerable to this attack, scan and fix with:
npx hackmyagent secure --verbose
This page tests CRED-001. Look for that check ID in the scan output.
The vulnerable agent may not be the only one on the machine. The shadow AI audit inventories the AI tools, MCP servers and governance gaps across it, running or installed, one row per agent project, worst first:
npx hackmyagent detect