microsoft-SkillOpt

mirror of https://github.com/microsoft/SkillOpt.git synced 2026-08-03 07:02:46 +08:00

Files

NovusEdge 4322656803 fix(adapters): sandbox the verification re-run; claude bin override (Copilot round 5)

Builds on 0a898b1 (docker uses bare `claude`). Addresses 2 findings on 49356f8:

- SECURITY: _harness_verify re-runs the (agent-modified) project code. It now
  goes through the same _sandbox_prefix as the agent when SKILLOPT_SANDBOX is
  set, so untrusted code isn't executed on the host during verification; in
  docker it uses the in-image `python3`. Default (no-sandbox) mode still runs on
  the host for trusted candidates, now documented with an explicit warning.
- Add SKILLOPT_CLAUDE_BIN to override the claude binary (Copilot's suggested
  explicit override), on top of the docker bare-name default.

Tests: 55 focused, full suite 315 passed / 6 skipped.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-07-23 03:02:59 +03:00

guide

refactor: make EnvAdapter.reflect a shared default (fixes dropped reflect kwargs)

2026-06-15 09:06:00 +00:00

reference

docs: align API reference and Add-a-Benchmark guide with real EnvAdapter ABC

2026-06-01 20:14:54 +00:00

sleep

chore(release): v0.2.0

2026-07-02 22:11:10 +08:00

superpowers

fix(adapters): sandbox the verification re-run; claude bin override (Copilot round 5)