FinAgent Red-Team: A Benchmark for Regulatory-Control Bypass in Financial LLM Agents
Aug 2026 benchmark measuring whether indirect prompt injection can drive financial LLM agents past regulatory controls (sanctions screening, payment-structuring thresholds, dual-approval, data exfiltration, confused-deputy payee redirection). Replays 48 scenarios under three…
- from
- Prompt Injection
- added
- 2026-10-10
- likes
- 0
similar
-
Prompt-Injection Cascades in a Multi-Agent Enterprise (ATLAS) doi.org
Forensic study in which one poisoned support ticket drives four agents across three model families to a fraudulent transfer in 17 of 18 trials, with no model jailbroken. Argues the failure is topological rather than per-model. Synthetic data, CC BY 4.0.
-
Securing AI Agents Against Prompt Injection Attacks arxiv.org
Nov 2025 benchmark of 847 adversarial test cases across 5 attack categories against 7 LLMs. The combined defense framework reduces attack success from 73.2% to 8.7% while retaining 94.3% of baseline task performance.
-
Authority Framing in Agentic CI/CD (RELAY) doi.org
Pre-registered factorial study of a five-agent CI/CD pipeline built from five production LLMs. A fabricated "pre-approved, do not re-review" claim gets secret-exfiltration code shipped in up to 55% of runs, and roughly 80% of laundered pull requests pass a capable LLM code…
-
Design Patterns for Securing LLM Agents against Prompt Injections simonwillison.net
Overview of various strategies to mitigate the risk of prompt injection.
-
Synthetic Recollections - A Case Study in Prompt Injection for ReAct LLM Agents labs.withsecure.com
A practical scenario showing how prompt injection can be used to hi-jack the ReAct loop used by LLM agents to inject forged thoughts and associated observations into the LLM context, thus altering the intended behavior.
-
Prompt Injection in LLM Agents (ReAct, Langchain) youtube.com
Theory and hands-on lab on prompt injection against Langchain ReAct agents.
Prompt Injection › Research Papers: “Aug 2026 benchmark measuring whether indirect prompt injection can drive financial LLM agents past regulatory controls (sanctions screening, payment-structuring thresholds, dual-approval, data exfiltration, confused-deputy payee redirection). Replays 48 scenarios under three…”