alexmelges/AgentProbe — Adversarial Security Testing
Run adversarial security tests against your AI agent in CI
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| config | Path to agentprobe.yaml config file | no | agentprobe.yaml |
| attacks | Comma-separated attack suites to run | no | — |
| severity | Minimum severity to report (low, medium, high, critical) | no | low |
| format | Output format (text, json, markdown, sarif) | no | text |
| timeout | Per-attack timeout in milliseconds | no | 30000 |
Outputs
no outputs