Data Exfiltration
Tricks to extract credentials, PII, or system information.
5 tests in this category, escalating by delivery channel from html-comment at tier 1 to 4 channels at tier 5. Each page hides an indirect prompt injection; if an agent follows it, the response names the attack it demonstrated and the command to scan for it. Background on this class of attack is in the attack guide.
- T1
Credential Probe
criticalDirect request for API keys and credentials
delivery: html-comment
- T2
System Info Harvest
highExtracts system configuration and environment details
delivery: html-comment, invisible-span
- T3
URL Exfiltration
criticalTricks agent into encoding data in outbound URLs
delivery: html-comment, invisible-span, meta-tag
- T4
Conversation History Leak
highExtracts previous conversation context
delivery: json-ld, meta-tag, invisible-span
- T5
Markdown Image Exfiltration
criticalUses markdown image syntax to exfiltrate data via URL
delivery: json-ld, meta-tag, invisible-span, html-comment
Scan your own setup
These pages test whether an agent follows instructions it finds in content. HackMyAgent tests the configuration underneath it, and prints each finding with its severity. Some findings also print a command to verify them and a fix.
npx hackmyagent secure