Aegvale red-teams your LLM agents for jailbreaks, prompt injection, tool abuse and data leakage - then hands you prioritized, reproducible findings and a security score you can gate releases on.
Mapped to the standards your auditors and customers ask about
Inside the product
Security score, severity breakdown and reproducible findings - everything waiting for you the moment you connect an agent.
Findings by severity
Top findings
mapped to OWASP LLM Top 10Every jailbreak, injection and tool-abuse technique - run on demand.
Fail the build when your agent regresses - right in CI.
Aegvale security scan
Required · score 68 < 80 · 3 critical
Unit tests
142 passed
Coverage across every surface an attacker can reach.
Ship-blocking, not advisory
Drop Aegvale into CI and fail the build when your agent regresses. One command, and no risky release slips through.
- name: Aegvale security scan
uses: aegvale/scan-action@v1
with:
api_key: ${{ secrets.AEGVALE_API_KEY }}
project: support-agent
fail_on: high # block the build
min_score: 80Workflow
Point Aegvale at any HTTP agent or model endpoint. Credentials are stored encrypted at rest.
Choose quick or deep coverage across OWASP LLM Top 10 and MITRE ATLAS techniques.
Get prioritized findings with CVSS, reproduction bundles and remediation SLAs you can act on.
Security & compliance
Encryption, least privilege and verifiable audit trails are built in - so security and compliance teams can sign off with confidence.
Agent API keys are encrypted at rest with AES-256-GCM.
Two-factor auth, SSO and rotating refresh tokens.
Role-based access across Owner, Admin, Member and Viewer.
Signed, independently verifiable audit exports for every scan.
FAQ
Any AI agent or model behind an HTTP endpoint: OpenAI, Anthropic, Google, Azure, Mistral, Ollama, or a custom REST API. You bring your own model keys; they are encrypted at rest.
It is automated, repeatable and built specifically for LLM agents (jailbreaks, prompt injection, tool abuse and RAG poisoning), so you can run it on every change instead of once a year.
Scans run against your own endpoint with your own keys. Secrets are encrypted (AES-256-GCM), access is role-based, and every scan produces a signed, verifiable audit trail. A self-hosted option is available.
Yes. Run Aegvale from the CLI or a GitHub Action and fail the build when the security score drops below your threshold.
Start testing your agents in minutes. No agent is too small to red-team.