Lineaje analyzed 5,505 malicious skill-category records across 75 unique malicious skill URLs to assess malicious AI skills.
Public source
Publisher name
Public post
AI skills may look like simple extensions to an agent. Lineaje research shows malicious ones can behave more like multi-purpose attack tools. Across 75 unique malicious…
Company
Lineaje
Lineaje secures AI and software supply chains autonomously, continuously, and across the full lifecycle.
- Industry
- Computer and Network Security
- Location
- Saratoga, US
- Company size
- 11–50 employees
About Lineaje
Lineaje's full-lifecycle software supply chain security is designed to meet the specific compliance, governance and automation needs of companies that source, build, deploy, sell or buy critical software. Its technology allows organizations to autonomously and effectively source safe software, contextualize risks, auto-secure builds, and manage risk and compliance. Customers use Lineaje to know what is in their software, eliminate vulnerability exposure, deploy self-healing containers, auto-fix all vulnerabilities and comply with global regulations. The company is trusted by top technology, financial and public sector organizations that must secure and manage critical code, complex software supply chains and large software portfolios.
See moreLatest activity
Latest activity from Lineaje
7 signals
Research & Knowledge
Lineaje published a research paper titled AI TAR VIDEO: An AI coding agent turned a routine repository read into a secret exfiltration pipeline — no jailbreak required, just the privilege it already had.
Research & Knowledge
Lineaje published a Build Secure or Be Forever Insecure White Paper analyzing 5,505 malicious skill-category records across 75 unique malicious skill URLs.
Research & Knowledge
Lineaje analyzed 5,505 malicious skill-category records across 75 unique malicious skill URLs to determine the average malicious skill was associated with 9.44 distinct malicious categories.
Discover more
Similar signals
Similar public activity from other companies.
Research & Knowledge
Cequence Security
Cequence Security published a research claim that a global financial services firm ran their first AI discovery scan expecting a manageable number of agents, finding 740% more MCP servers, 800% more AI agents, and 600% more LLM providers than anticipated.
Research & Knowledge
FireTail.ai
FireTail.ai tracked 302 AI security incidents this year.
Research & Knowledge
Cybersecurity Insiders
Cybersecurity Insiders published the 2026 CISO AI Risk Report, which reveals that 92% of enterprises are blind to AI agents operating in their environments.
Research & Knowledge
MIND
MIND surveyed 124 CISOs and found that 90% of enterprises have deployed AI and 70% struggle to enforce security policies around it.
Research & Knowledge
UltraViolet Cyber