A recent study analyzing nearly 80,000 AI agent skills found that a significant portion, 48.5%, of all installs are on code pushed within the last seven days. This indicates a highly active and rapidly evolving ecosystem for AI agent extensions, contrary to expectations of a decaying digital graveyard. The research also highlights that the riskiest code, defined by being shell-capable and unaudited, is predominantly found in actively maintained repositories rather than stale ones, suggesting that security audits should prioritize install count and permission surface over last commit dates. AI
IMPACT Highlights the rapid iteration and potential security risks within the AI agent extension ecosystem.
RANK_REASON Analysis of a dataset on AI agent skills, not a primary release or significant industry event. [lever_c_demoted from research: ic=1 ai=1.0]
Read on dev.to — Claude Code tag →
- Anthropic
- Claude
- Claude Code
- codex
- Cursor
- design-doc-mermaid
- humanizer-zh
- OpenAI
- Skillselion
- The Agent Skill Maintenance Census
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
