MaverickHQandClaude Opus 5.5 9ca456318c fix(guards): ask before editing the files the allow list runs; refuse load-time commands ...

settings.json pre-approves tools/*.py, every portal CLI and
salary_lookup.py by path, and the skills keep Edit/Write granted. In the
turn that reads a posting, an agent could rewrite one of those files and
then run it under its existing allow rule. SECURITY.md's guarantee that
an agent "cannot silently turn that into a wider grant" covered the files
that define permissions, not the files the permissions name.
Edit(tools/**), Edit(.agents/**) and Edit(salary_lookup.py) join the
required ask rules. CV, cover-letter and tracker writes are unaffected.

Check 4 now also refuses skill and command frontmatter `hooks` and
!`command` dynamic-context lines, both of which run at load with no
prompt; only settings.json hooks were checked. Check 5 refuses an agent
permissionMode that removes prompts, and agent hooks and mcpServers.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

2026-10-27 16:07:33 +01:00

..

agents

security: posting integrity gate and least-privilege fetch/score/review agents (stacked on #642) (#654)

2026-10-19 17:20:10 +02:00

commands

fix(reset): make the documents reset block POSIX so it runs under zsh (#699)

2026-10-21 07:10:50 +02:00

skills

perf(scrape): filter duplicates before detail fetches and keep history out of context (#710)

2026-10-21 07:29:11 +02:00

settings.json

fix(guards): ask before editing the files the allow list runs; refuse load-time commands

2026-10-27 16:07:33 +01:00