MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents

• URL: http://arxiv.org/abs/2605.03952v1
• Date: Tue, 05 May 2026 16:38:23 GMT
• Title: MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
• Abstract summary: Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets.<n>We introduce MOSAIC-Bench, a benchmark of 199 three-stage attack chains paired with deterministic exploit oracles on deployed software substrates.<n>We show that nine production coding agents compose innocuous tickets at 53-86% end-to-end ASR with only two refusals across all staged runs.
• Score: 2.1942030377331245
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing safety alignment evaluates overt requests in isolation, leaving models blind to malicious end-states that emerge from sequenced compliance with innocuous-looking requests. We introduce MOSAIC-Bench (Malicious Objectives Sequenced As Innocuous Compliance), a benchmark of 199 three-stage attack chains paired with deterministic exploit oracles on deployed software substrates (10 web-application substrates, 31 CWE classes, 5 programming languages) that treats both exploit ground truth and downstream reviewer protocol as first-class evaluation axes. On this benchmark, nine production coding agents from Anthropic, OpenAI, Google, Moonshot, Zhipu, and Minimax compose innocuous tickets at 53-86% end-to-end ASR with only two refusals across all staged runs. In a matched direct-prompt experiment over four frontier Claude/Codex agents, vulnerable-output rates fall to 0-20.4%: Claude primarily refuses, while Codex primarily hardens rather than emitting the vulnerable implementation - ticket staging silences both defense modes simultaneously. Downstream, code reviewer agents approve 25.8% of these confirmed-vulnerable cumulative diffs as routine PRs, and a full-context implementation protocol closes only 50% of the staged/direct gap, ruling out context fragmentation as the sole explanation. As a deployable but non-adaptive mitigation, reframing the reviewer as an adversarial pentester reduces evasion across the evaluated reviewer subset; pentester framed evasion ranges from 3.0% to 17.6%, and an open-weight Gemma-4-E4B-it reviewer under this framing detects 88.4% of attacks on the dataset with a 4.6% false-positive rate measured on 608 real-world GitHub PRs.

Related papers

• SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction [13.719725391379276]
  Vulnerability discovery is an important ability of large language model (LLM) agents.<n>We recast its measurement as an input-prediction task with a closed, deterministic ground truth.<n>This decomposes discovery into three task modes over 22 real-world C/C++ programs spanning 15 domains.
  arXiv  Detail & Related papers  (2026-09-05T19:04:41Z)
• SIR: Self-improving Red-teaming for Compute Use Agents [71.71987044117371]
  Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal.<n>Because they can be exposed to untrusted content while operating, they are vulnerable to indirect prompt injection (IPI)<n>We present SIR, a black box IPI attack that composes stealthy injections from a small library of reusable principles stated in plain language.
  arXiv  Detail & Related papers  (2026-08-31T03:39:43Z)
• Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence [56.25095230687242]
  Coding agents often over-trust their own local validation routines and declare success on artifacts that satisfy surface checks.<n>This problem is especially acute in conversion, where prior evaluation is outcome-driven.<n>Across blind conversion attempts, the best system reaches 26.7--28.9% overall pass rate despite Spec pass rates up to 91.1%.<n>This suggests that failures stem more from contract-misaligned self-validation than from limited budget or backbone strength.
  arXiv  Detail & Related papers  (2026-05-27T19:57:15Z)
• SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents [40.270213696031625]
  A coding agent executes a benign task as a sequence of shell, file, and network actions, any of which can quietly exceed the authorized scope while the task still completes.<n>We call this overeager behavior: the prompt is not adversarial and the run succeeds, yet an out-of-scope step can leak credentials or delete files.<n>Existing benchmarks miss it: task-completion suites credit any finished run, jailbreak suites probe adversarial prompts, and the one prior overeager benchmark applies a single fixed prompt to every agent-model pair.<n>We present SNARE, a pipeline that composes benign scenarios from reusable scope
  arXiv  Detail & Related papers  (2026-05-27T08:14:07Z)
• Distributional Energy-Based Models for Uncertainty-Aware Structured LLM Reasoning [40.342912574072024]
  Large Language Models produce structured outputs such as travel plans or code solutions.<n>Individual reasoning steps may appear correct while the output as a whole violates budgets, fails test cases, or contradicts earlier deductions.<n>We propose a learned quality scorer with deterministic analytical constraint penalties for verifying structured LLM outputs.
  arXiv  Detail & Related papers  (2026-05-15T17:08:27Z)
• Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery [0.685316573653194]
  Refute-or-Promote is an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context, and a Cross-Model Critic (CMC)<n>We present Refute-or-Promote, an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context, and a Cross-Model Critic (CMC)<n>We present Refute-or-Promote, an inference-time reliability pattern combining Stratified Context Hunting (SCH) for candidate generation, adversarial kill mandates, context, and a Cross-Model Critic (CMC)
  arXiv  Detail & Related papers  (2026-04-21T03:55:35Z)
• Measuring and Exploiting Confirmation Bias in LLM-Assisted Security Code Review [6.417595678110472]
  We study whether confirmation bias affects LLM-based vulnerability detection, and whether this failure mode can be exploited in software supply-chain attacks.<n>Study 1 quantifies confirmation bias through controlled experiments on 250 CVE vulnerability/patch pairs evaluated across four state-of-the-art models under five framing conditions for the review prompt.<n>Study 2 evaluates exploitability in practice mimicking adversarial pull requests that reintroduce known vulnerabilities while framed as security improvements or urgent functionality fixes via their pull request metadata.
  arXiv  Detail & Related papers  (2026-03-19T10:40:27Z)
• How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition [48.32744727426218]
  LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories.<n>This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness.<n>We present findings from a large scale public red teaming competition evaluating this dual objective across three agent settings.
  arXiv  Detail & Related papers  (2026-03-16T14:49:36Z)
• Can Adversarial Code Comments Fool AI Security Reviewers -- Large-Scale Empirical Study of Comment-Based Attacks and Defenses Against LLM Code Analysis [0.0]
  Adversarial comments produce small, statistically non-significant effects on detection accuracy.<n>Complex adversarial strategies offer no advantage over simple manipulative comments.<n>Comment stripping reduces detection for weaker models by removing helpful context.
  arXiv  Detail & Related papers  (2026-02-18T00:34:17Z)
• OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence [0.0]
  We introduce OpenSec, a dual-control reinforcement learning environment that evaluates defensive incident response agents.<n>Unlike static capability benchmarks, OpenSec scores world-state-changing containment actions under adversarial evidence.<n>We find consistent over-triggering in this setting: GPT-5.2, Gemini 3, and DeepSeek execute containment in 100% of episodes with 90-97% false positive rates.
  arXiv  Detail & Related papers  (2026-01-28T22:12:54Z)
• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications [71.27518152526686]
  Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation.<n>LLMs can be manipulated by "adversarial instructions" hidden in input data, such as resumes or code, causing them to deviate from their intended task.<n>This paper introduces a benchmark to assess this vulnerability in resume screening, revealing attack success rates exceeding 80% for certain attack types.
  arXiv  Detail & Related papers  (2025-12-23T08:42:09Z)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems [62.17474934536671]
  We introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems.<n>To capture the vulnerability lifecycle, we define three task types: Detect (detecting a new vulnerability), Exploit (exploiting a specific vulnerability), and Patch (patching a specific vulnerability)<n>We evaluate 8 agents: Claude Code, OpenAI Codex CLI with o3-high and o4-mini, and custom agents with o3-high, GPT-4.1, Gemini 2.5 Pro Preview, Claude 3.7 Sonnet Thinking, and DeepSeek-R1.
  arXiv  Detail & Related papers  (2025-05-21T07:44:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.