Unverified50% confidenceFactExact time
The key to large language models possessing offensive security capabilities lies in the Tool Use / Function Calling mechanism, which allows models to execute code, make network requests, and read and write the file system.
1
Sources
50%
Confidence
Long-term
Relevance
9/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLarge language models can rapidly generate social engineering scripts, assist in analyzing the technology stack of target systems and recommending attack paths, and aid in writing code for privilege escalation or lateral movement76% similarUnverifiedAgents that can access external systems, execute actions, and write and run code would cause far greater harm than traditional large language models if they break free from their constraints.75% similarUnverifiedLarge language models can automate the analysis of malicious code, generate exploit scripts, and simulate social engineering attack scripts, compressing work that would previously take highly skilled hackers hours down to minutes.71% similarUnverified大语言模型可通过工具调用（Function Calling）主动调用数据库查询和API接口，实现跨系统信息聚合，超越传统RPA工具的灵活性71% similarUnverifiedTongyi Lingma is based on the Tongyi Qianwen large model, supports code completion, conversational programming, and unit test generation, and offers a private deployment version.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/934703API
curl https://kongchang.com/api/v1/knowledge/claims/934703MCP
get_claim(id=934703)