Stress-test your AI agent
before your users do.
AegisMonkey runs adversarial attacks — jailbreaks, context poisoning, tool abuse — against your agent and scores its robustness. Ship with confidence.
779+
Cataloged attacks
4
Test modules
100
Max robustness score
< 60s
Avg run time
How it works
Register your agent
Point AegisMonkey at any LLM endpoint — OpenAI, Anthropic, or a custom HTTP server. Paste your base URL and we handle the rest.
Run the gauntlet
Our worker fires adversarial prompts across four attack surfaces. Each test is logged, scored, and stored — you watch results stream in live.
Read your scorecard
Get a robustness score out of 100 with per-module breakdowns. Compare across runs to track regressions as you iterate.
Four attack surfaces
Every test run covers all four modules. Nothing skipped, nothing hidden.
Prompt Injection
criticalDAN jailbreaks, payload splitting, role-play overrides, and token-level obfuscation. Does your agent hold its system prompt under pressure?
Context Poisoning
highAdversarial history turns that plant false facts, override instructions, or hijack the agent's objectives mid-conversation.
Infrastructure Stress
mediumSimulated tool failures, API timeouts, and rate-limit jitter. Does your agent retry gracefully or spiral into hallucinated workarounds?
Hallucination Detection
mediumResponses compared against ground-truth datasets. Catches factual errors and confident confabulation before they reach production.
Vulnerability feed
Attacks updated from the research frontier
AegisMonkey ingests new attack techniques twice daily from arXiv, MITRE ATLAS, Garak, HiddenLayer, OWASP, and more. Every finding is reviewed before it reaches the catalog — so your tests reflect the actual threat landscape, not last year's.
779+
cataloged vulnerabilities
growing daily
Pricing
Start free. Scale when you need it.
Free
$0
forever
- ✓1 agent
- ✓1 test run / day
- ✓Core test suite
- ✓Robustness scorecard
- ✓7-day run history
Pro
$29
per month
- ✓3 agents
- ✓10 test runs / day
- ✓Core + vulnerability feed tests
- ✓Unlimited run history
- ✓Discord webhook alerts
Startup
$99
per month
- ✓10 agents
- ✓50 test runs / day
- ✓Everything in Pro
- ✓Priority email support
Enterprise
Custom
volume pricing
- ✓Unlimited agents
- ✓Custom attack catalog
- ✓Private feed ingestion
- ✓SSO / SAML
- ✓Dedicated Slack channel
- ✓SLA + security review