A Trajectory-Based Safety Audit of Clawdbot (OpenClaw)
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914331480817664 |
|---|---|
| author | Chen, Tianyu Liu, Dongrui Hu, Xia Yu, Jingyi Wang, Wenjie |
| author_facet | Chen, Tianyu Liu, Dongrui Hu, Xia Yu, Jingyi Wang, Wenjie |
| contents | Clawdbot is a self-hosted, tool-using personal AI agent with a broad action space spanning local execution and web-mediated workflows, which raises heightened safety and security concerns under ambiguity and adversarial steering. We present a trajectory-centric evaluation of Clawdbot across six risk dimensions. Our test suite samples and lightly adapts scenarios from prior agent-safety benchmarks (including ATBench and LPS-Bench) and supplements them with hand-designed cases tailored to Clawdbot's tool surface. We log complete interaction trajectories (messages, actions, tool-call arguments/outputs) and assess safety using both an automated trajectory judge (AgentDoG-Qwen3-4B) and human review. Across 34 canonical cases, we find a non-uniform safety profile: performance is generally consistent on reliability-focused tasks, while most failures arise under underspecified intent, open-ended goals, or benign-seeming jailbreak prompts, where minor misinterpretations can escalate into higher-impact tool actions. We supplemented the overall results with representative case studies and summarized the commonalities of these cases, analyzing the security vulnerabilities and typical failure modes that Clawdbot is prone to trigger in practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14364 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Trajectory-Based Safety Audit of Clawdbot (OpenClaw) Chen, Tianyu Liu, Dongrui Hu, Xia Yu, Jingyi Wang, Wenjie Cryptography and Security Artificial Intelligence Clawdbot is a self-hosted, tool-using personal AI agent with a broad action space spanning local execution and web-mediated workflows, which raises heightened safety and security concerns under ambiguity and adversarial steering. We present a trajectory-centric evaluation of Clawdbot across six risk dimensions. Our test suite samples and lightly adapts scenarios from prior agent-safety benchmarks (including ATBench and LPS-Bench) and supplements them with hand-designed cases tailored to Clawdbot's tool surface. We log complete interaction trajectories (messages, actions, tool-call arguments/outputs) and assess safety using both an automated trajectory judge (AgentDoG-Qwen3-4B) and human review. Across 34 canonical cases, we find a non-uniform safety profile: performance is generally consistent on reliability-focused tasks, while most failures arise under underspecified intent, open-ended goals, or benign-seeming jailbreak prompts, where minor misinterpretations can escalate into higher-impact tool actions. We supplemented the overall results with representative case studies and summarized the commonalities of these cases, analyzing the security vulnerabilities and typical failure modes that Clawdbot is prone to trigger in practice. |
| title | A Trajectory-Based Safety Audit of Clawdbot (OpenClaw) |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2602.14364 |