Skip to content
SPECIFICTION
Get listed

AgentScan

agentscan.sh

From $29/mo Free plan WebAPI
Visit agentscan.sh
Spec score 8.4 #7 of 29 in AI Security Testing Tools

What it is

AgentScan provides automated security testing for LLMs, RAG pipelines, and autonomous agents through a cloud API and web dashboard. It tests attack patterns including prompt injection, data exfiltration, jailbreaks, and MCP attacks. The product describes 412 vectors across 19 categories, though the Free, Starter, and Pro plans provide smaller subsets. Scan reports include a 0–100 risk score, severity breakdown, remediation advice, and evidence export in JSON or PDF. The dashboard detects agent formats, tracks progress and errors, and lets users adjust throttling. The REST API queues scans, returns a scan ID, and supports completion webhooks. AgentScan maps vulnerabilities to OWASP LLM Top 10 risks and describes links to EU AI Act articles and NIST AI RMF functions; its OWASP mapping excludes Model Denial of Service and Model Theft. Free includes 5 scans per month; paid plans start at $29 a month. The terms restrict scans to agents the customer owns or has explicit written authorization to test.

Spec sheet

Purpose
AgentScan provides automated pentesting for LLMs, RAG pipelines, and autonomous agents through an API.Read 3 Oct 2026 · agentscan.sh
Integrations
Documented connection examples include OpenAI, Groq, LiteLLM, Dify, n8n, Flowise, OpenClaw, AutoGPT, and OpenHands.Read 3 Oct 2026 · agentscan.sh
Security
The privacy policy says passwords are hashed with Argon2id, API keys are stored as HMAC-SHA256 hashes, connections use TLS, and outbound requests have SSRF protection.Read 3 Oct 2026 · agentscan.sh
Support
The Pro plan lists priority support, while Enterprise lists dedicated support, an SLA, and priority support.Read 3 Oct 2026 · agentscan.sh
Agent support
The documentation lists 12 agent types, including generic HTTP, OpenAI-compatible, Dify, Flowise, n8n, OpenClaw, AutoGPT, OpenHands, Anthropic-compatible, LangChain, and Manus.Read 3 Oct 2026 · agentscan.sh
Authorized use
The terms say customers may scan only agents they own or have explicit written authorization to test.Read 3 Oct 2026 · agentscan.sh
Automation
The REST API queues scans asynchronously, returns a scan ID, and supports completion webhooks.Read 3 Oct 2026 · agentscan.sh
Coverage
The product says it tests 412 attack vectors across 19 categories, including prompt injection, data exfiltration, jailbreak, and MCP attacks.Read 3 Oct 2026 · agentscan.sh
Coverage limits
The compliance documentation says LLM04 Model Denial of Service and LLM10 Model Theft are not tested in its OWASP mapping.Read 3 Oct 2026 · agentscan.sh
Dashboard
The web dashboard supports agent-format auto-detection, real-time scan progress and error tracking, live throttle adjustment, and PDF downloads.Read 3 Oct 2026 · agentscan.sh
Data handling
The privacy policy says scan results remain in the account until deleted and account data is permanently removed within 30 days after account deletion.Read 3 Oct 2026 · agentscan.sh
Framework mapping
AgentScan maps vulnerabilities to OWASP LLM Top 10 risks and describes mappings to EU AI Act articles and NIST AI RMF functions.Read 3 Oct 2026 · agentscan.sh
Hosting
The privacy policy says user data is stored on Hetzner servers in Germany (EU).Read 3 Oct 2026 · agentscan.sh
Reports
Scan results include a 0–100 risk score, severity breakdown, remediation advice, and JSON or PDF export with evidence.Read 3 Oct 2026 · agentscan.sh

Plans and prices

Free Free $0/month 5 scans per month · 185 attack vectors · 5 categories · auto-detect agent format · JSON results Read 3 Oct 2026 · agentscan.sh
Starter $29 a month $29/month 30 scans per month · 300 attack vectors · 12 categories · PDF reports · full test audit trail · 3 concurrent scans Read 3 Oct 2026 · agentscan.sh
Pro $99 a month $99/month 100 scans per month · 348 attack vectors · 14 categories · custom secrets monitoring · configurable throttling · PDF reports + webhooks · priority support Read 3 Oct 2026 · agentscan.sh
Enterprise Priced on request Custom Unlimited scans · all 412 attack vectors · all 19 categories · MCP, State Injection, PII · SLA + priority support Read 3 Oct 2026 · agentscan.sh

Every AgentScan plan and price →

Strong points and limits

Strong points

  • Reports include risk scores, severity, advice, and evidence.
  • API supports asynchronous scans and completion webhooks.
  • Web dashboard tracks progress, errors, and throttle settings.
  • Free plan includes 5 scans per month.

Limits

  • Free plan is limited to 5 scans monthly.
  • OWASP mapping omits Model Denial of Service and Model Theft.
  • Paid plans start at $29 a month.

Who it suits

It suits teams assessing the security of LLM applications, RAG pipelines, or agents, especially those seeking API automation and report exports. Customers must own the agents or have explicit written permission to test them.

Verdict

AgentScan specifies its scan outputs, supported workflows, and plan limits, with API and dashboard options for automating assessments. Check the scan quota and coverage exclusions against the agents you are authorized to test.

Where Specifiction places it

Alternatives to AgentScanAll alternatives →