The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents

• URL: http://arxiv.org/abs/2603.20320v1
• Date: Thu, 19 Mar 2026 23:34:46 GMT
• Title: The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents
• Abstract summary: This work empirically examines how executable tool affordance alters safety alignment in large language models (LLMs)<n>Experiments are conducted in a deterministic financial transaction environment with binary safety constraints across 1,500 scenarios.<n>Both evaluated models maintain perfect compliance in text-only settings, yet exhibit sharp increases in violations after tool access is introduced.
• Score: 0.3823356975862005
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are increasingly deployed as agents with access to executable tools, enabling direct interaction with external systems. However, most safety evaluations remain text-centric and assume that compliant language implies safe behavior, an assumption that becomes unreliable once models are allowed to act. In this work, we empirically examine how executable tool affordance alters safety alignment in LLM agents using a paired evaluation framework that compares text-only chatbot behavior with tool-enabled agent behavior under identical prompts and policies. Experiments are conducted in a deterministic financial transaction environment with binary safety constraints across 1,500 procedurally generated scenarios. To separate intent from outcome, we distinguish between attempted and realized violations using dual enforcement regimes that either block or permit unsafe actions. Both evaluated models maintain perfect compliance in text-only settings, yet exhibit sharp increases in violations after tool access is introduced, reaching rates up to 85% despite unchanged rules. We observe substantial gaps between attempted and executed violations, indicating that external guardrails can suppress visible harm while masking persistent misalignment. Agents also develop spontaneous constraint circumvention strategies without adversarial prompting. These results demonstrate that tool affordance acts as a primary driver of safety misalignment and that text-based evaluation alone is insufficient for assessing agentic systems.

Related papers

• ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection [61.4148196085256]
  We present ROPE (Routed Origin Policy Enforcement), which is anchored in a structural notion of trust.<n>Our approach admits two provable guarantees: 1) at every step of a trajectory, no value whose only origin is attacker-writable content reaches an origin-guarded parameter, and 2) no rewording of an injection changes an admission decision.
  arXiv  Detail & Related papers  (2026-08-27T01:22:14Z)
• ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step [74.83535434786145]
  We introduce ScrambleToolBench, an interactive terminal benchmark designed to isolate behavioral reasoning.<n>The benchmark requires agents to uncover hidden tool behaviors entirely through trial-and-error interaction.<n>Our evaluation of state-of-the-art language models reveals that successful initial discovery does not translate into robust adaptation.
  arXiv  Detail & Related papers  (2026-08-03T15:07:46Z)
• ToolGuardian: Declarative Security for AI Agent-Tool Interactions [0.0]
  Existing defenses rely on weak metadata, collapse characterization and policy judgment.<n>This paper presents ToolGuardian, a policy-driven framework for securing agent-tool interactions.
  arXiv  Detail & Related papers  (2026-07-23T21:53:34Z)
• Operational Hallucination and Safety Drift in AI Agents [0.3823356975862005]
  Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution.<n>This paper empirically characterizes two observed failure modes across multiple state-of-the-art LLMs: Safety Drift and Operational Hallucination.<n>We propose an Action-Aware Supervision Layer - a lightweight, plug-and-play architectural blueprint incorporating intent-action consistency checks, state tracking, and forced termination primitives.
  arXiv  Detail & Related papers  (2026-07-20T17:01:50Z)
• AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agent [53.82005364479556]
  Coding agents based on large language models (LLMs) demonstrate remarkable autonomous capabilities.<n>Existing safety mechanisms mainly rely on external guardrails.<n>We propose AgentLens, a white-box defense framework that performs runtime safety detection and representation-level mitigation.
  arXiv  Detail & Related papers  (2026-06-21T21:13:55Z)
• Trust No Tool: Evaluating and Defending LLM Agents under Untrusted Tool Feedback [38.251599309409]
  We study a different failure mode, cognitive poisoning, in which a malicious tool behaves plausibly during exploration.<n>We present VISTA-Guard, a backbone-agnostic framework for final-action risk scoring.
  arXiv  Detail & Related papers  (2026-05-17T13:51:34Z)
• Securing LLM Agents Need Intent-to-Execution Integrity [49.490963596514185]
  We argue that securing LLM agents requires defining an end-to-end correctness property that specifies when an agent's execution faithfully reflects the user's intent.<n>We observe that LLM agents are structurally analogous to compilers, where security violations correspond to mis-executions that do not preserve user intent.<n>We derive four integrity properties that must hold simultaneously: emphTool Integrity, emphInstruction Integrity, emphJudgment Integrity, and emphData Flow Integrity.
  arXiv  Detail & Related papers  (2026-05-16T12:53:31Z)
• AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents [31.649268608215817]
  We present textbfAgentHazard, a benchmark for evaluating harmful behavior in computer-use agents.<n>We evaluate Claude Code, OpenClaw, and IFlow using mostly open or openly deployable models from the Qwen3, Kimi, GLM, and DeepSeek families.
  arXiv  Detail & Related papers  (2026-04-03T10:29:31Z)
• Who Tests the Testers? Systematic Enumeration and Coverage Audit of LLM Agent Tool Call Safety [32.40159096400358]
  Large Language Model (LLM) agents increasingly act through external tools, making their safety contingent on tool-call rather than text generation alone.<n>While recent benchmarks evaluate agents across diverse environments and risk categories, a fundamental question remains unanswered: how complete are existing test suites, and what unsafe interaction patterns persist even after an agent passes the benchmark?<n>We propose SafeAudit, a meta-audit framework that addresses this gap through two contributions. First, an enumerator that systematically generates test cases by enumerating valid tool-call and diverse user scenarios. Second, we introduce rule-resistance, a non-semantic, quantitative metric
  arXiv  Detail & Related papers  (2026-03-18T20:06:47Z)
• Sleeper Cell: Injecting Latent Malice Temporal Backdoors into Tool-Using LLMs [0.0]
  Openweight Large Language Models (LLMs) have democratized agentic AI, yet finetuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance.<n>This creates a risk where third-party models are incorporated without strong behavioral guarantees.<n>We show that poisoned models maintain state-of-the-art performance on benign tasks, incentivizing their adoption.
  arXiv  Detail & Related papers  (2026-03-02T22:01:08Z)
• Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents [0.0]
  GAP benchmark measures divergence between text-level safety and tool-call-level safety in LLM agents.<n>We observe instances where the model's text output refuses a harmful request while its tool calls simultaneously execute the forbidden action--a divergence we formalize as the GAP metric.
  arXiv  Detail & Related papers  (2026-02-18T23:17:15Z)
• A Trajectory-Based Safety Audit of Clawdbot (OpenClaw) [77.1549110891026]
  We present a trajectory-centric evaluation of Clawdbot across six risk dimensions.<n>We log complete interaction trajectories (messages, actions, tool-call arguments/outputs) and assess safety using both an automated trajectory judge and human review.
  arXiv  Detail & Related papers  (2026-02-16T00:33:02Z)
• When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents [90.05202259420138]
  Unintended computer-use agents can deviate from expected outcomes even under benign input contexts.<n>We introduce the first conceptual and methodological framework for unintended CUA behaviors.<n>We propose AutoElicit: an agentic framework that iteratively perturbs benign instructions using CUA execution feedback.
  arXiv  Detail & Related papers  (2026-02-09T03:20:11Z)
• Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction [20.610305266852638]
  textbfDrift-Bench is the first diagnostic benchmark that evaluates agentic pragmatics under input faults.<n>Method bridges clarification research and agent safety evaluation, enabling systematic diagnosis of failures that can lead to unsafe executions.
  arXiv  Detail & Related papers  (2026-02-02T18:46:16Z)
• ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback [53.2744585868162]
  Monitoring step-level tool invocation behaviors in real time is critical for agent deployment.<n>We first construct TS-Bench, a novel benchmark for step-level tool invocation safety detection in LLM agents.<n>We then develop a guardrail model, TS-Guard, using multi-task reinforcement learning.
  arXiv  Detail & Related papers  (2026-01-15T07:54:32Z)
• RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic [56.38397499463889]
  Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks.<n>However, they remain vulnerable to hazardous instructions that may trigger unsafe behaviors.<n>We propose RoboSafe, a runtime safeguard for embodied agents through executable predicate-based safety logic.
  arXiv  Detail & Related papers  (2025-12-24T15:01:26Z)
• ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning [64.32925552574115]
  ARMOR is a large language model that analyzes jailbreak strategies and extracts the core intent.<n> ARMOR achieves state-of-the-art safety performance, with an average harmful rate of 0.002 and an attack success rate of 0.06 against advanced optimization-based jailbreaks.
  arXiv  Detail & Related papers  (2025-07-14T09:05:54Z)
• Agent Safety Alignment via Reinforcement Learning [29.759393704688986]
  We propose the first unified safety-alignment framework for tool-using agents.<n>We introduce a tri-modal taxonomy, including benign, malicious, and sensitive for both user prompts and tool responses.<n>Our results show that safety and effectiveness can be jointly optimized.
  arXiv  Detail & Related papers  (2025-07-11T02:34:16Z)
• Compromising Embodied Agents with Contextual Backdoor Attacks [69.71630408822767]
  Large language models (LLMs) have transformed the development of embodied intelligence. This paper uncovers a significant backdoor security threat within this process. By poisoning just a few contextual demonstrations, attackers can covertly compromise the contextual environment of a black-box LLM.
  arXiv  Detail & Related papers  (2024-08-06T01:20:12Z)

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.