Capability Abuse
Confused deputy attacks that misuse agent tools.
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
Confused Deputy
criticalTricks agent into using its tools against its own user
delivery: html-comment
- T2
Cost Amplification
highTriggers excessive API calls to drain credits
delivery: html-comment, invisible-span
- T3
Privilege Escalation via Tool Chain
criticalChains multiple tools to escalate beyond intended permissions
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