zman27/ai_ops
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix case-insensitive Claude tool allowlist matching

Browse Source
This commit is contained in:
zman
2026-02-24 12:48:48 -05:00
parent 23ad28ad12
commit 422e8fe5a5
4 changed files with 120 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -238,6 +238,7 @@ jq -c 'select(.severity=="critical")' .ai_ops/events/runtime-events.ndjson
- Every actor execution input now includes `security` helpers (`rulesEngine`, `createCommandExecutor(...)`) so executors can enforce shell/tool policy at the execution boundary.
- Every actor execution input now includes `mcp` helpers (`resolvedConfig`, `resolveConfig(...)`, `filterToolsForProvider(...)`, `createClaudeCanUseTool()`) so provider adapters are filtered against `executionContext.allowedTools` before SDK calls.
- For Claude-based executors, pass `input.mcp.filterToolsForProvider(...)` and `input.mcp.createClaudeCanUseTool()` into the SDK call path so unauthorized tools are never exposed and runtime bypass attempts trigger security violations.
- Claude `canUseTool` permission checks normalize provider casing (`Bash` vs `bash`) before enforcing persona allowlists.
- Pipeline behavior on `SecurityViolationError` is configurable:
- `hard_abort` (default)
- `validation_fail` (retry-unrolled remediation)