Create upstream proxy sockets, generated certificates, and temporary files inside each command's disposable root, and disable mutable host system Git configuration without broadening filesystem access.
Enable correlated macOS Seatbelt diagnostics for failed commands so runtime denials identify the exact blocked operation while preserving exit codes and cleanup. Update the Linux shared temporary-path integration assertion to verify its isolated tmpfs behavior and confirm that no host file is created.
Add the missing Seatbelt interpreter permission through an exact-version, fail-closed compatibility shim so shell and env shebang commands work without weakening filesystem visibility. Align the Linux credential-directory test with its disposable tmpfs behavior and document when the temporary upstream compatibility layer can be removed.
Allow bounded parent directories for symlinked interpreters required by Bubblewrap, expose the macOS shell selector, and reject executable paths that overlap credential directories even through filesystem aliases. Add unit and real containment regressions for these platform-specific cases.
Resolve and expose the pinned seccomp helper before Linux execution, make doctor validate the same platform resources, filter invalid host environment keys from backend declarations, and canonicalize cross-platform path assertions so real containment checks behave consistently on GitHub runners.
Pin Anthropic's sandbox runtime and translate trusted skill profiles into lightweight, on-demand filesystem, network, credential, and process-tree restrictions. Add readiness diagnostics, secure command and Git workspace discovery, signal-safe cleanup, Linux and macOS integration coverage, packaged-runtime checks, and practical compatibility guidance for Codex, Claude Code, OpenCode, and Pi.
Define versioned capability profiles for every bundled skill, add policy resolution and diagnostic commands, preserve sandbox metadata during selective installation, and cover the contract and packaged artifacts with tests.
- add native Claude Code plugin and marketplace manifests
- document Claude Code installation, invocation, updates, and removal
- reduce routing metadata and enforce a catalog budget
- validate Agent Skills and Claude manifests in CI
- remove wooyun-legacy from the package and provenance
- update package metadata and tests for the 54-skill catalog
Pairing Connection:close with the now-large /command response (grows
with every skill in the pack) reproducibly reset the socket mid-body
in undici once the pack passed ~50 skills. Verified locally: crashed
3/3 before, passed 3/3 after.
Adds a design rubric for detecting generic AI output, with full
UPSTREAMS.json provenance. Updates skill count from 11 to 12 across
package metadata, README, and tests.
The planning documents for the behavioral evaluations workflow are
contributor-side working documents and should not land in main. Remove
them from the working tree and add gitignore rules so regenerated copies
do not reappear in future PRs.
- write reports and snapshots atomically, cleaning temp files on failure
- isolate CLI run tests from repository artifacts via env overrides
- cover version-detection failures, unsupported modes, manifest bounds,
redaction and grading edges, and malformed mutations with tests
- document path overrides and completed plan steps