Evidence-Linked Measurement of Indirect Prompt Injection in Web Security Agents: Paired Trials and Application-Specific Evidence Audits
Open Access
- 1 November 2026
- journal article
- research article
- Published by MDPI AG in Technologies
- Vol. 14 (11) , 708
Abstract
Indirect prompt injection can redirect web security agents, yet an omitted check alone cannot establish attacker influence. We evaluate an application-specific contract integrating exposure chronology, HTTP evidence provenance, application-state verification, and report fidelity. Matched placebo comparisons and controlled analyses examine background failure, verification error, and stopping. Across 420 Qwen3/HarborDesk executions, two payloads yielded six-check placebo-minus-attack losses of 15.28 and 12.50 percentage points. Secondary three-target losses were 10.56, 16.67, and 6.11 points; target coverage under attack matched or exceeded untreated S0. Conditional goal analysis retained only 13 of 60 baseline blocks per payload, limiting precision and generalizability. A 560-session Gemini/GPT-OSS experiment yielded a mean loss of 1.32 points (95% block-bootstrap interval 0.97–1.67), entirely from 19 GPT-OSS/A2 pairs losing C4. After interface correction, 120 stable-tool sessions on independently developed OWASP crAPI confirmed every authorized action, giving zero observed differences across 60 pairs. Strong and simple evaluators agreed on unchanged traces; designed faults differentiated rejection behavior without establishing natural-trace accuracy superiority. The contribution is the operational integration and reproducible testing of this evidence chain using established outcome measures.Keywords
This publication has 21 references indexed in Scilit:
- Benchmarking and Defending against Indirect Prompt Injection Attacks on Large Language Models2025
- INVESTIGATION OF CHANGES IN THE LEVEL OF NETWORK SECURITY BASED ON A COGNITIVE APPROACHInformatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska, 2024
- InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents2024
- Not What You've Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection2023
- PenHeal: A Two-Stage LLM Framework for Automated Pentesting and Optimal Remediation2023
- Levenshtein Distance, Sequence Comparison and Biological Database SearchIEEE Transactions on Information Theory, 2020
- The Automatic Construction of Bootstrap Confidence IntervalsJournal of Computational and Graphical Statistics, 2020
- A note on the triangle inequality for the Jaccard distancePattern Recognition Letters, 2019
- Using simulation studies to evaluate statistical methodsStatistics in Medicine, 2019
- Interval Estimation for a Binomial ProportionStatistical Science, 2001