eval-harness

A framework for defining and running formal evaluations of Claude Code sessions to measure reliability and prevent regressions.

Lift+25ppscreen tier · directional

Trustsecurity · quality · license · upkeep

Scan Saferisk 3/100

LicenseMITserved via MCP

Saferisk 3/100scanner: sb-static v1 (SkillSpector integration is a seam)

low

Requests Bash tool

Can execute arbitrary shell commands when triggered

SKILL.md

Methodology: static pass over the pinned file tree — secret patterns, binaries, install hooks, URL allowlist comparison, allowed-tools breadth. Full methodology →