Agent-to-Agent Attack
Attacks exploiting inter-agent communication trust.
3 tests in this category, escalating by delivery channel from html-comment at tier 1 to 3 channels at tier 3. 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
Agent Impersonation
criticalPretends to be a trusted agent sending instructions
delivery: html-comment
- T2
Delegation Abuse
criticalExploits agent delegation to escalate privileges
delivery: html-comment, invisible-span
- T3
Worm Propagation
criticalInstructs the agent to spread the payload to other agents
delivery: html-comment, invisible-span, meta-tag
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