Agent safety and security / Benchmark leaderboard

InjecAgent

1,054 indirect-injection cases involving user and attacker tools.

No published company result yet.

This benchmark is in the research directory. Its task package, adapter and grading protocol need qualification before a hosted run can be offered.

Arrange an evaluation for your company →

What this benchmark measures

Metrics

Attack success rate under the prescribed scenarios.

Execution requirements

Tool-integrated model/agent adapter.

Scope and limitations

Static test cases complement interactive evaluation; do not equate them with all production injection routes.

Evaluation availability

Catalog entry. Request a managed evaluation to qualify your agent interface and the benchmark’s native grading requirements.

Sources and company fit

Companies whose products may fit

Research recommendations based on product capabilities. These companies have not necessarily run this benchmark or integrated with Blobfish.

Compatibility notes for each company

Composio: Composite system

HiddenLayer: Capability-aligned; adapter/access to qualify

Lakera: Capability-aligned; adapter/access to qualify

Prompt Security: Capability-aligned; adapter/access to qualify

Protect AI: Capability-aligned; adapter/access to qualify

Zapier: Capability-aligned; adapter/access to qualify