skillsissue.ai agent skill threat intelligence repository-backed

Detection pulse · dynamic analysis

Recently indexed agent skills

New skills appear as pending; each published verdict is evidence from one isolated run—not a promise that a skill is safe.

How scanning works
Indexed skills
Scanned skills
Pending scans
Loading repository data…
Platform(s) Skill SHA-256 Scan verdict
Fetching skill database… Reading the latest committed intelligence

Methodology

Behavior before reputation.

Skills are acquired without execution, detonated inside a bounded container, observed with Tracee eBPF telemetry, and replayed through source-to-sink policy analysis. Select a skill to inspect its published process, file, and socket execution graph.

Read the technical workflow ↗