github/openclaw
1
1
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-02-19 18:39:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

chore (changelog): note memory-lancedb injection hardening

Browse Source
This commit is contained in:
Vignesh Natarajan
2026-02-14 18:19:47 -08:00
parent 61725fb37e
commit 3ca74f8e6d
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
CHANGELOG.md
View File

@@ -56,6 +56,7 @@ Docs: https://docs.openclaw.ai
- Memory/QMD: query QMD index using exact docid matches before falling back to prefix lookup for better recall correctness and index efficiency.
- Memory/QMD: make QMD result JSON parsing resilient to noisy command output by extracting the first JSON array from noisy `stdout`.
- Memory/QMD: treat prefixed `no results found` marker output as an empty result set in qmd JSON parsing. (#11302) Thanks @blazerui.
- Security/Memory-LanceDB: treat recalled memories as untrusted context (escape injected memory text + explicit non-instruction framing), skip likely prompt-injection payloads during auto-capture, and restrict auto-capture to user messages to reduce memory-poisoning risk. (#12524) Thanks @davidschmid24.
- Memory/Builtin: narrow memory watcher targets to markdown globs and ignore dependency/venv directories to reduce file-descriptor pressure during memory sync startup. (#11721) Thanks @rex05ai.
- Memory/QMD: make `memory status` read-only by skipping QMD boot update/embed side effects for status-only manager checks.
- Memory/QMD: keep original QMD failures when builtin fallback initialization fails (for example missing embedding API keys), instead of replacing them with fallback init errors.