Towards a Risk Assessment of Malicious Skill Files in Coding Agents

arXiv 2608.05223•9623dc5a63b2f607b8d7ff125919e8b187ed5acb3ba754fe2c7daf2dc9d1ab1c
AI securityLLM securityMITRE ATT&CKagent skillsautonomous agentscoding agentscommand executiondeveloper toolsmalicious filesprompt injectionsecurity assessmentsoftware supply chain

Paper metadata

arXiv ID
2608.05223
Version
Not specified by this published record
Category
Computer Science — Software Engineering (cs.SE)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_cs_se
Record identifier
9623dc5a63b2f607b8d7ff125919e8b187ed5acb3ba754fe2c7daf2dc9d1ab1c
Enrichment time
2026-08-07T08:51:40Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.

Towards a Risk Assessment of Malicious Skill Files in Coding Agents · Baitaphish