PulseAugur
EN
LIVE 20:27:36

AI agent skills: 82% unchecked, 1 in 32 unsafe

By PulseAugur Editorial · [1 sources] ·

A security analysis of 117,854 AI agent skills revealed that a significant majority (82.3%) have never been graded for safety. Among the skills that were assessed, approximately 1 in 32 were found to be unsafe or have security concerns. The study also identified a new attack surface related to agent configuration and memory theft, highlighting that risks are concentrated in less popular, long-tail skills rather than widely used ones. AI

IMPACT Highlights critical security gaps in AI agent ecosystems, potentially slowing adoption until trust layers mature.

RANK_REASON Security analysis of AI agent skills with statistical findings. [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — MCP tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

AI agent skills: 82% unchecked, 1 in 32 unsafe

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Security analysis of AI agent skills with statistical findings. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
95 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — MCP tag TIER_1 English(EN) · yansen zhu ·

    We security-graded 117,854 AI agent skills. Here's what we found.

    <p>Only 17.7% of the catalog is popular enough to be graded, 1 in 32 graded skills is unsafe, and the risk lives in the long tail — plus a new agent-native attack surface.<br /> </p> <div class="crayons-card c-embed text-styles text-styles--secondary"> <div class="c-embed__conten…

RELATED ENTITIES

RELATED TOPICS