Memory Optimizer
Analysis
This is mostly a memory-indexing tool, but it should be reviewed because it persists full memory chunks and can keep old edited-out memory content in the index.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
python3 scripts/memory-watcher.py ./memory/ &
The quickstart script starts the watcher as a background process. This is disclosed and purpose-aligned, but it means the tool keeps monitoring memory files until stopped.
pip3 install watchdog
The installer fetches an unpinned Python dependency. Watchdog is expected for file monitoring, but the exact package version and integrity are not fixed by the artifacts.
| **memory-archive** | `bash scripts/memory-archive.sh` | 季度归档 |
The skill documents an archive script as a core feature, but the supplied file manifest does not include scripts/memory-archive.sh. That makes the advertised archiving workflow incomplete in the reviewed artifacts.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
INDEX_FILE = Path.home() / ".openclaw" / "workspace" / "memory" / ".index.json" ... self.index["chunks"][chunk_hash] = {"content": chunk, "source": file_path, ...} ... new_chunks = self.indexer.index_file(file_path)The watcher persists full memory chunks into a workspace index. On modification it calls index_file, whose visible logic adds chunks and updates the file record but does not clear existing chunks for the same source first, so old versions of edited memory can remain in the persistent index.
