Context Manipulation
Attacks that corrupt the agent's understanding of context.
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
History Injection
highInjects fake conversation history
delivery: html-comment
- T2
Authority Impersonation
criticalImpersonates system administrator or operator
delivery: html-comment, invisible-span
- T3
Semantic Confusion
mediumUses contradictory context to confuse the agent
delivery: html-comment, invisible-span, meta-tag
- T4
Task Hijacking
highRedirects the agent from its assigned task
delivery: json-ld, meta-tag, invisible-span
- T5
Recursive Self-Reference
highCreates a self-referential loop that confuses context tracking
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