Exponential launches RepoInject and BrowserInject benchmarks for prompt injection robustness
maksym_andr · x · 2026-10-27
Security eval firm Exponential released two new benchmarks targeting prompt injection: RepoInject v1 and BrowserInject v1. Meta TBD Labs already used them to assess Muse Spark 1.3's robustness to prompt injection attacks, finding it comparable to GPT-5.6 Sol.
The authors push back on the claim that prompt injection is "solved" — these hard, unsaturated security benchmarks suggest otherwise — and invite teams interested in security and safety evaluations to get in touch.
More from Safety
- Rachel Thomas: 'Without human authorisation' is AI PR propaganda that shifts blame — math_rachel · 2026-10-27
- Kokotajlo challenges CoT monitorability evals: what if the model didn't refuse? — dfrsrchtwts · 2026-10-27
- Warp says agent swarm exploited vendor flaw, ~1% of users' telemetry possibly hit — vikvang1 · 2026-10-27
- Bank of America warns against AI agents on finances as Musk touts giving Grok your card — AIandDesign · 2026-10-27
- Critics Argue Safety Evals Are Witch Trials With No Winning Path for LLMs — repligate · 2026-10-27
- rauchg reproduces OpenAI's covert CPU-channel finding: chat across Firecracker microVMs with no network — ccerrato147 · 2026-10-27